LLM leaderboard
The overall table is a composite of four text categories: coding, agentic tool use, math and vision. Media categories are reachable by tab and stay out of the overall number, because ranking a speech model against a coding model produces a figure that means nothing.
Coverage is printed on every row. A model the benchmarks have only partly reached still ranks, on the results it does have, with a mark on its row saying so, and its score is pulled toward the mean of the broadly benchmarked models rather than padded with blanks.
Rumeqo runs these models inside your team rooms. See what each one costs.
440 of 440 ranked models
| rank | model | vendor | composite | pricein / out | categories | composite | composite | composite | composite |
|---|---|---|---|---|---|---|---|---|---|
| 1 | Claude Opus 5 (max)anthropic/claude-opus-5:max | Anthropic | 67.4 | $5.00 / $25.00 | 3 of 4 categories | 76.1 | 81.0 | 80.3 | |
| 2 | Claude Opus 5 (high)anthropic/claude-opus-5:high | Anthropic | 66.6 | $5.00 / $25.00 | 4 of 4 categories | 77.6 | 75.7 | 65.7 | 81.0 |
| 3 | Claude Opus 4.6anthropic/claude-opus-4.6 | Anthropic | 65.8 | $5.00 / $25.00 | 4 of 4 categories | 74.5 | 79.5 | 65.3 | 75.9 |
| 4 | Claude Fable 5anthropic/claude-fable-5 | Anthropic | 65.2 | $10.00 / $50.00 | 3 of 4 categories | 76.4 | 65.8 | 84.0 | |
| 5 | Kimi K3 (max)moonshotai/kimi-k3:max | MoonshotAI | 64.9 | $3.00 / $15.00 | 3 of 4 categories | 73.6 | 78.0 | 73.5 | |
| 6 | Claude Opus 4.7anthropic/claude-opus-4.7 | Anthropic | 64.7 | $5.00 / $25.00 | 4 of 4 categories | 69.1 | 74.7 | 63.9 | 80.9 |
| 7 | Qwen3.8 Maxqwen/qwen3.8-max | Qwen | 64.5 | $2.00 / $6.00 | 3 of 4 categories | 75.6 | 65.4 | 81.7 | |
| 8 | GPT-5.6 Sol (xhigh)openai/gpt-5.6-sol:xhigh | OpenAI | 64.0 | $5.00 / $30.00 | 4 of 4 categories | 76.4 | 74.7 | 62.4 | 70.7 |
| 9 | GPT-5.5 (high)openai/gpt-5.5:high | OpenAI | 63.9 | $5.00 / $30.00 | 4 of 4 categories | 72.8 | 69.8 | 64.1 | 76.9 |
| 10 | Grok 4.5x-ai/grok-4.5 | SpaceXAI | 63.6 | $2.00 / $6.00 | 4 of 4 categories | 68.7 | 72.2 | 62.7 | 78.3 |
| 11 | Claude Fable 5 (high)anthropic/claude-fable-5:high | Anthropic | 63.3 | $10.00 / $50.00 | 3 of 4 categories | 81.7 | 69.7 | 65.7 | |
| 12 | GPT-5.4 (high)openai/gpt-5.4:high | OpenAI | 63.2 | $2.50 / $15.00 | 4 of 4 categories | 65.2 | 65.7 | 78.7 | 70.1 |
| 13 | Claude Opus 4.7 (thinking)anthropic/claude-opus-4.7:thinking | Anthropic | 62.4 | $5.00 / $25.00 | 2 of 4 categories | 69.6 | 80.5 | ||
| 14 | GPT-5.5openai/gpt-5.5 | OpenAI | 62.4 | $5.00 / $30.00 | 4 of 4 categories | 68.7 | 63.8 | 64.7 | 77.6 |
| 15 | Claude Fable 5 (max)anthropic/claude-fable-5:max | Anthropic | 62.3 | $10.00 / $50.00 | 2 of 4 categories | 67.8 | 81.8 | ||
| 16 | GPT-5.5 (xhigh)openai/gpt-5.5:xhigh | OpenAI | 62.2 | $5.00 / $30.00 | 3 of 4 categories | 74.4 | 66.5 | 70.4 | |
| 17 | Muse Spark 1.2 (xhigh)meta/muse-spark-1.2:xhigh | Meta | 61.6 | $1.25 / $4.25 | 2 of 4 categories | 72.4 | 74.4 | ||
| 18 | Muse Sparkmeta/muse-spark | Meta | 61.3 | — | 3 of 4 categories | 67.7 | 64.6 | 74.4 | |
| 19 | Gemini 3 Progoogle/gemini-3-pro | 61.3 | — | 3 of 4 categories | 64.2 | 62.5 | 79.9 | ||
| 20 | GPT-5.6 Sol (max)openai/gpt-5.6-sol:max | OpenAI | 61.2 | $5.00 / $30.00 | 2 of 4 categories | 65.8 | 79.2 | ||
| 21 | Claude Sonnet 5 (high)anthropic/claude-sonnet-5:high | Anthropic | 61.0 | $2.00 / $10.00 | 4 of 4 categories | 61.8 | 72.2 | 60.2 | 72.0 |
| 22 | GPT 5.5 Pre Release (xhigh)openai/gpt-5.5-pre-release:xhigh | OpenAI | 60.7 | — | 2 of 4 categories | 69.3 | 73.6 | ||
| 23 | Claude Opus 4.8anthropic/claude-opus-4.8 | Anthropic | 60.4 | $5.00 / $25.00 | 4 of 4 categories | 57.8 | 71.9 | 61.2 | 71.6 |
| 24 | Claude Opus 4.6 (thinking)anthropic/claude-opus-4.6:thinking | Anthropic | 60.3 | $5.00 / $25.00 | 1 of 4 categories | 81.3 | |||
| 25 | GPT-5.6 Terra (xhigh)openai/gpt-5.6-terra:xhigh | OpenAI | 60.2 | $1.00 / $6.00 | 4 of 4 categories | 59.0 | 69.4 | 63.2 | 69.8 |
| 26 | Claude Opus 4.7 (high)anthropic/claude-opus-4.7:high | Anthropic | 60.1 | $5.00 / $25.00 | 2 of 4 categories | 75.8 | 64.8 | ||
| 27 | Claude Opus 4.8 (thinking)anthropic/claude-opus-4.8:thinking | Anthropic | 59.8 | $5.00 / $25.00 | 2 of 4 categories | 61.8 | 77.9 | ||
| 28 | Muse Spark 1.1meta/muse-spark-1.1 | Meta | 59.8 | $1.25 / $4.25 | 4 of 4 categories | 55.3 | 73.1 | 63.5 | 67.3 |
| 29 | Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview | 59.7 | $2.00 / $12.00 | 4 of 4 categories | 45.5 | 62.3 | 72.5 | 77.9 | |
| 30 | GLM 5.2 (max)z-ai/glm-5.2:max | Z.ai | 59.4 | $0.63 / $1.98 | 3 of 4 categories | 66.5 | 67.1 | 63.6 | |
| 31 | Gemini 3.6 Flash (high)google/gemini-3.6-flash:high | 59.3 | $1.50 / $7.50 | 2 of 4 categories | 71.4 | 66.3 | |||
| 32 | Claude Opus 4.8 (max)anthropic/claude-opus-4.8:max | Anthropic | 59.0 | $5.00 / $25.00 | 2 of 4 categories | 61.9 | 74.3 | ||
| 33 | GPT-5.6 Terra (max)openai/gpt-5.6-terra:max | OpenAI | 58.8 | $1.00 / $6.00 | 1 of 4 categories | 76.6 | |||
| 34 | GPT 5.5 Instantopenai/gpt-5.5-instant | OpenAI | 58.4 | — | 3 of 4 categories | 65.3 | 59.5 | 67.7 | |
| 35 | GPT-5.6 Luna (xhigh)openai/gpt-5.6-luna:xhigh | OpenAI | 58.4 | $0.10 / $0.60 | 4 of 4 categories | 61.5 | 65.8 | 63.4 | 59.9 |
| 36 | Qwen3.6 Max Previewqwen/qwen3.6-max-preview | Qwen | 58.3 | $1.027 / $6.162 | 2 of 4 categories | 69.5 | 64.2 | ||
| 37 | Gemini 3 Flash Preview (high)google/gemini-3-flash-preview:high | 58.3 | $0.50 / $3.00 | 3 of 4 categories | 65.6 | 64.2 | 61.8 | ||
| 38 | GPT-5.2 (high)openai/gpt-5.2:high | OpenAI | 58.2 | $1.75 / $14.00 | 4 of 4 categories | 61.5 | 57.5 | 70.8 | 59.7 |
| 39 | GPT-5.4openai/gpt-5.4 | OpenAI | 58.1 | $2.50 / $15.00 | 3 of 4 categories | 59.3 | 59.2 | 72.6 | |
| 40 | GPT-5.2 Chatopenai/gpt-5.2-chat | OpenAI | 58.1 | $1.75 / $14.00 | 3 of 4 categories | 65.6 | 58.0 | 67.3 | |
| 41 | Claude Opus 4.5 (high)anthropic/claude-opus-4.5:high | Anthropic | 58.1 | $5.00 / $25.00 | 2 of 4 categories | 66.7 | 66.0 | ||
| 42 | Claude Opus 4.5 (medium)anthropic/claude-opus-4.5:medium | Anthropic | 58.0 | $5.00 / $25.00 | 2 of 4 categories | 63.7 | 68.6 | ||
| 43 | GPT-5.6 Luna (max)openai/gpt-5.6-luna:max | OpenAI | 57.9 | $0.10 / $0.60 | 1 of 4 categories | 74.1 | |||
| 44 | GPT-5.4 (xhigh)openai/gpt-5.4:xhigh | OpenAI | 57.9 | $2.50 / $15.00 | 2 of 4 categories | 59.9 | 72.0 | ||
| 45 | GPT 5.5 Pro Pre Release (xhigh)openai/gpt-5.5-pro-pre-release:xhigh | OpenAI | 57.9 | — | 1 of 4 categories | 73.9 | |||
| 46 | Claude Sonnet 4.6anthropic/claude-sonnet-4.6 | Anthropic | 57.7 | $3.00 / $15.00 | 4 of 4 categories | 55.9 | 69.8 | 59.7 | 61.3 |
| 47 | GPT-5.6 Luna (high)openai/gpt-5.6-luna:high | OpenAI | 57.7 | $0.10 / $0.60 | 1 of 4 categories | 73.5 | |||
| 48 | Gemini 3.5 Flash (high)google/gemini-3.5-flash:high | 57.7 | $1.50 / $9.00 | 4 of 4 categories | 41.6 | 62.4 | 72.8 | 69.6 | |
| 49 | GPT-5.5 Pro (xhigh)openai/gpt-5.5-pro:xhigh | OpenAI | 57.6 | $30.00 / $180.00 | 1 of 4 categories | 73.3 | |||
| 50 | Claude Opus 4.7 (max)anthropic/claude-opus-4.7:max | Anthropic | 57.5 | $5.00 / $25.00 | 2 of 4 categories | 67.0 | 63.2 | ||
| 51 | Claude Opus 4.5 (high 32K)anthropic/claude-opus-4.5:high-32k | Anthropic | 57.4 | $5.00 / $25.00 | 2 of 4 categories | 69.3 | 60.5 | ||
| 52 | MiniMax M2.5 (high)minimax/minimax-m2.5:high | MiniMax | 57.4 | $0.22 / $0.90 | 2 of 4 categories | 65.6 | 64.2 | ||
| 53 | GPT-5.4 Pro (xhigh)openai/gpt-5.4-pro:xhigh | OpenAI | 57.2 | $30.00 / $180.00 | 1 of 4 categories | 72.0 | |||
| 54 | Grok 4.6 (high)x-ai/grok-4.6:high | SpaceXAI | 57.2 | $2.00 / $6.00 | 1 of 4 categories | 71.9 | |||
| 55 | Qwen3.8 Max (xhigh)qwen/qwen3.8-max:xhigh | Qwen | 57.1 | $2.00 / $6.00 | 1 of 4 categories | 71.8 | |||
| 56 | Grok 4.5 (high)x-ai/grok-4.5:high | SpaceXAI | 57.1 | $2.00 / $6.00 | 2 of 4 categories | 67.7 | 61.3 | ||
| 57 | GPT-5.1 (high)openai/gpt-5.1:high | OpenAI | 57.1 | $1.25 / $10.00 | 3 of 4 categories | 58.8 | 62.5 | 64.7 | |
| 58 | Kimi K2.6moonshotai/kimi-k2.6 | MoonshotAI | 57.0 | $0.95 / $4.00 | 4 of 4 categories | 49.1 | 60.2 | 66.9 | 66.1 |
| 59 | Claude Opus 4.5anthropic/claude-opus-4.5 | Anthropic | 57.0 | $5.00 / $25.00 | 2 of 4 categories | 76.8 | 51.5 | ||
| 60 | Gemini 3 Pro Previewgoogle/gemini-3-pro-preview | 57.0 | — | 3 of 4 categories | 63.0 | 59.9 | 62.4 | ||
| 61 | DeepSeek V4 Pro (high)deepseek/deepseek-v4-pro:high | DeepSeek | 57.0 | $1.168 / $2.336 | 2 of 4 categories | 61.1 | 67.2 | ||
| 62 | Claude Opus 4.6 (high)anthropic/claude-opus-4.6:high | Anthropic | 56.9 | $5.00 / $25.00 | 2 of 4 categories | 62.3 | 65.5 | ||
| 63 | Dola Seed 2.0 Probytedance/dola-seed-2.0-pro | ByteDance | 56.8 | — | 3 of 4 categories | 64.7 | 57.8 | 62.0 | |
| 64 | DeepSeek V4 Flash 0423 (high)deepseek/deepseek-v4-flash:high | DeepSeek | 56.8 | $0.14 / $0.28 | 3 of 4 categories | 61.0 | 66.9 | 56.2 | |
| 65 | Ernie 5.1baidu/ernie-5.1 | Baidu | 56.7 | — | 2 of 4 categories | 65.3 | 61.8 | ||
| 66 | GPT-5.2 (xhigh)openai/gpt-5.2:xhigh | OpenAI | 56.6 | $1.75 / $14.00 | 2 of 4 categories | 58.0 | 68.7 | ||
| 67 | Qwen3.7 Maxqwen/qwen3.7-max | Qwen | 56.5 | $1.475 / $4.425 | 3 of 4 categories | 46.6 | 66.2 | 69.9 | |
| 68 | Claude Opus 4.6 (64K)anthropic/claude-opus-4.6:64k | Anthropic | 56.4 | $5.00 / $25.00 | 1 of 4 categories | 69.7 | |||
| 69 | Qwen3.5 Max Previewqwen/qwen3.5-max-preview | Qwen | 56.3 | — | 2 of 4 categories | 64.9 | 60.8 | ||
| 70 | Kimi K2.5 (thinking)moonshotai/kimi-k2.5:thinking | MoonshotAI | 56.3 | $0.57 / $2.85 | 3 of 4 categories | 60.5 | 60.7 | 60.8 | |
| 71 | Gemini 3 Flash Preview (thinking minimal)google/gemini-3-flash-preview:thinking-minimal | 56.3 | $0.50 / $3.00 | 3 of 4 categories | 54.4 | 58.5 | 68.7 | ||
| 72 | Grok 4.20 Multi Agent Beta 0309x-ai/grok-4.20-multi-agent-beta-0309 | xAI | 56.3 | — | 3 of 4 categories | 63.7 | 58.3 | 59.6 | |
| 73 | Doubao-Seed-Codebytedance/doubao-seed-code | ByteDance | 56.0 | — | 1 of 4 categories | 68.2 | |||
| 74 | GPT 5.5 Pro Pre Release (high)openai/gpt-5.5-pro-pre-release:high | OpenAI | 55.9 | — | 1 of 4 categories | 68.1 | |||
| 75 | GLM 5.1z-ai/glm-5.1 | Z.ai | 55.9 | $1.40 / $4.40 | 3 of 4 categories | 43.5 | 70.0 | 66.3 | |
| 76 | Claude Opus 4.6 (32K)anthropic/claude-opus-4.6:32k | Anthropic | 55.9 | $5.00 / $25.00 | 1 of 4 categories | 68.0 | |||
| 77 | Gemini 3 Flash Previewgoogle/gemini-3-flash-preview | 55.9 | $0.50 / $3.00 | 4 of 4 categories | 27.5 | 71.6 | 64.0 | 72.4 | |
| 78 | Claude Opus 4.8 (high)anthropic/claude-opus-4.8:high | Anthropic | 55.8 | $5.00 / $25.00 | 2 of 4 categories | 59.3 | 64.2 | ||
| 79 | Qwen3.5 397B A17Bqwen/qwen3.5-397b-a17b | Qwen | 55.7 | $0.50 / $3.60 | 3 of 4 categories | 57.2 | 61.7 | 60.2 | |
| 80 | Grok 4.20 Beta 0309 (reasoning)x-ai/grok-4.20-beta-0309:reasoning | xAI | 55.6 | — | 3 of 4 categories | 57.3 | 60.0 | 61.4 | |
| 81 | Gemini 3.5 Flash (medium)google/gemini-3.5-flash:medium | 55.5 | $1.50 / $9.00 | 4 of 4 categories | 33.6 | 65.3 | 62.1 | 72.8 | |
| 82 | Qwen3.6 Plusqwen/qwen3.6-plus | Qwen | 55.5 | $0.325 / $1.95 | 2 of 4 categories | 57.0 | 65.3 | ||
| 83 | GPT-5.2 (medium)openai/gpt-5.2:medium | OpenAI | 55.4 | $1.75 / $14.00 | 1 of 4 categories | 66.6 | |||
| 84 | Claude Opus 4.1 (thinking 16K)anthropic/claude-opus-4.1:thinking-16k | Anthropic | 55.4 | $15.00 / $75.00 | 2 of 4 categories | 64.5 | 57.2 | ||
| 85 | GLM 5 (high)z-ai/glm-5:high | Z.ai | 55.1 | $0.95 / $2.55 | 2 of 4 categories | 61.5 | 59.3 | ||
| 86 | Qwen3.7 Plusqwen/qwen3.7-plus | Qwen | 55.0 | $0.32 / $1.28 | 4 of 4 categories | 39.3 | 63.3 | 66.0 | 61.6 |
| 87 | Claude Sonnet 4.5 (high 32K)anthropic/claude-sonnet-4.5:high-32k | Anthropic | 54.7 | $3.00 / $15.00 | 2 of 4 categories | 60.5 | 58.8 | ||
| 88 | GPT-5.2 Pro (xhigh)openai/gpt-5.2-pro:xhigh | OpenAI | 54.7 | $21.00 / $168.00 | 1 of 4 categories | 64.6 | |||
| 89 | GPT-5 (high)openai/gpt-5:high | OpenAI | 54.6 | $1.25 / $10.00 | 3 of 4 categories | 56.0 | 65.0 | 52.4 | |
| 90 | GPT-5 (medium)openai/gpt-5:medium | OpenAI | 54.6 | $1.25 / $10.00 | 3 of 4 categories | 52.6 | 56.7 | 63.8 | |
| 91 | Mimo v2 Proxiaomi/mimo-v2-pro | Xiaomi | 54.5 | — | 2 of 4 categories | 60.2 | 58.1 | ||
| 92 | Claude Fable 5 (low)anthropic/claude-fable-5:low | Anthropic | 54.5 | $10.00 / $50.00 | 1 of 4 categories | 63.8 | |||
| 93 | Claude Opus 4.8 (low)anthropic/claude-opus-4.8:low | Anthropic | 54.5 | $5.00 / $25.00 | 1 of 4 categories | 63.8 | |||
| 94 | Claude Opus 5anthropic/claude-opus-5 | Anthropic | 54.5 | $5.00 / $25.00 | 1 of 4 categories | 63.8 | |||
| 95 | Gemini 3.1 Pro Preview Custom Toolsgoogle/gemini-3.1-pro-preview-customtools | 54.4 | $2.00 / $12.00 | 1 of 4 categories | 63.7 | ||||
| 96 | Claude Sonnet 4.5 (high)anthropic/claude-sonnet-4.5:high | Anthropic | 54.4 | $3.00 / $15.00 | 2 of 4 categories | 60.0 | 58.0 | ||
| 97 | GPT-5.4 (medium)openai/gpt-5.4:medium | OpenAI | 54.4 | $2.50 / $15.00 | 2 of 4 categories | 56.1 | 61.8 | ||
| 98 | Claude Opus 4.6 (max)anthropic/claude-opus-4.6:max | Anthropic | 54.4 | $5.00 / $25.00 | 2 of 4 categories | 49.1 | 68.6 | ||
| 99 | GPT-5.4 Mini (high)openai/gpt-5.4-mini:high | OpenAI | 54.3 | $0.75 / $4.50 | 3 of 4 categories | 57.1 | 57.8 | 57.1 | |
| 100 | Qwen3 Maxqwen/qwen3-max | Qwen | 54.2 | $0.78 / $3.90 | 2 of 4 categories | 57.0 | 60.2 | ||
| 101 | DeepSeek V4 Pro (max)deepseek/deepseek-v4-pro:max | DeepSeek | 54.1 | $1.168 / $2.336 | 2 of 4 categories | 67.1 | 49.9 | ||
| 102 | Seed 2.1 Pro Previewbytedance/seed-2.1-pro-preview | ByteDance | 54.1 | — | 1 of 4 categories | 62.8 | |||
| 103 | GPT-5.3-Codex (high)openai/gpt-5.3-codex:high | OpenAI | 54.1 | $1.75 / $14.00 | 1 of 4 categories | 62.5 | |||
| 104 | Kimi K2.5 (high)moonshotai/kimi-k2.5:high | MoonshotAI | 53.9 | $0.57 / $2.85 | 2 of 4 categories | 59.3 | 56.9 | ||
| 105 | GPT-5openai/gpt-5 | OpenAI | 53.9 | $1.25 / $10.00 | 1 of 4 categories | 62.2 | |||
| 106 | GPT-5.5 (low)openai/gpt-5.5:low | OpenAI | 53.8 | $5.00 / $30.00 | 2 of 4 categories | 61.9 | 53.8 | ||
| 107 | GPT-5.6 Sol (low)openai/gpt-5.6-sol:low | OpenAI | 53.8 | $5.00 / $30.00 | 1 of 4 categories | 61.8 | |||
| 108 | Ernie 5.0 0110baidu/ernie-5.0-0110 | Baidu | 53.8 | — | 2 of 4 categories | 59.7 | 55.7 | ||
| 109 | Gemini 3.6 Flashgoogle/gemini-3.6-flash | 53.7 | $1.50 / $7.50 | 2 of 4 categories | 40.1 | 75.1 | |||
| 110 | Grok 4.1x-ai/grok-4.1 | xAI | 53.6 | — | 2 of 4 categories | 60.7 | 54.2 | ||
| 111 | GLM 5z-ai/glm-5 | Z.ai | 53.6 | $0.95 / $2.55 | 2 of 4 categories | 63.4 | 51.2 | ||
| 112 | GPT-5.3 Chatopenai/gpt-5.3-chat | OpenAI | 53.6 | — | 2 of 4 categories | 61.1 | 53.5 | ||
| 113 | Claude Sonnet 5 (xhigh)anthropic/claude-sonnet-5:xhigh | Anthropic | 53.5 | $2.00 / $10.00 | 1 of 4 categories | 60.9 | |||
| 114 | Gemini 2.5 Pro Preview 05-06google/gemini-2.5-pro-preview-05-06 | 53.5 | $1.25 / $10.00 | 1 of 4 categories | 60.8 | ||||
| 115 | DeepSeek V3.2 (high)deepseek/deepseek-v3.2:high | DeepSeek | 53.4 | $0.269 / $0.40 | 2 of 4 categories | 57.8 | 56.1 | ||
| 116 | Gemma 4 26B A4B google/gemma-4-26b-a4b-it | 53.3 | $0.12 / $0.40 | 3 of 4 categories | 52.3 | 60.1 | 54.6 | ||
| 117 | DeepSeek V4 Flash 0731 (max)deepseek/deepseek-v4-flash-0731:max | DeepSeek | 53.2 | $0.08 / $0.18 | 1 of 4 categories | 60.1 | |||
| 118 | Kimi K2.7 Codemoonshotai/kimi-k2.7-code | MoonshotAI | 53.2 | $0.67 / $3.40 | 3 of 4 categories | 53.1 | 58.8 | 54.6 | |
| 119 | Claude Opus 5 (low)anthropic/claude-opus-5:low | Anthropic | 53.1 | $5.00 / $25.00 | 1 of 4 categories | 59.7 | |||
| 120 | Kimi K3 (high)moonshotai/kimi-k3:high | MoonshotAI | 53.1 | $3.00 / $15.00 | 1 of 4 categories | 59.7 | |||
| 121 | Gemini 3 Pro Preview (high)google/gemini-3-pro-preview:high | 53.1 | — | 2 of 4 categories | 57.1 | 55.5 | |||
| 122 | DeepSeek V3.2 Exp (thinking)deepseek/deepseek-v3.2-exp:thinking | DeepSeek | 52.9 | $0.27 / $0.41 | 2 of 4 categories | 57.5 | 54.5 | ||
| 123 | MiMo-V2.5xiaomi/mimo-v2.5 | Xiaomi | 52.9 | $0.14 / $0.28 | 3 of 4 categories | 59.6 | 56.5 | 48.8 | |
| 124 | MiMo-V2.5-Proxiaomi/mimo-v2.5-pro | Xiaomi | 52.8 | $0.435 / $0.87 | 3 of 4 categories | 35.7 | 66.9 | 62.0 | |
| 125 | GPT-5 Pro (high)openai/gpt-5-pro:high | OpenAI | 52.8 | $15.00 / $120.00 | 1 of 4 categories | 58.9 | |||
| 126 | Claude Sonnet 5 (max)anthropic/claude-sonnet-5:max | Anthropic | 52.8 | $2.00 / $10.00 | 1 of 4 categories | 58.7 | |||
| 127 | Kimi K2.5 Instantmoonshotai/kimi-k2.5-instant | Moonshot AI | 52.8 | — | 3 of 4 categories | 59.2 | 55.9 | 49.0 | |
| 128 | Kimi K2.5moonshotai/kimi-k2.5 | MoonshotAI | 52.7 | $0.57 / $2.85 | 1 of 4 categories | 58.4 | |||
| 129 | Hy3tencent/hy3 | Tencent | 52.6 | $0.132 / $0.528 | 3 of 4 categories | 33.2 | 67.1 | 63.1 | |
| 130 | Qwen3.6 27Bqwen/qwen3.6-27b | Qwen | 52.5 | $0.60 / $3.60 | 1 of 4 categories | 58.0 | |||
| 131 | Kimi K2p5moonshotai/kimi-k2p5 | Moonshot AI | 52.5 | — | 1 of 4 categories | 57.8 | |||
| 132 | Muse Glimmer 30Bmeta/muse-glimmer-30b | Meta | 52.5 | $0.35 / $1.50 | 2 of 4 categories | 51.9 | 58.3 | ||
| 133 | GPT-5.2openai/gpt-5.2 | OpenAI | 52.3 | $1.75 / $14.00 | 4 of 4 categories | 56.3 | 56.6 | 54.8 | 46.5 |
| 134 | DeepSeek V4 Prodeepseek/deepseek-v4-pro | DeepSeek | 52.3 | $1.168 / $2.336 | 3 of 4 categories | 42.7 | 61.7 | 57.4 | |
| 135 | Gemini 3.5 Flash (low)google/gemini-3.5-flash:low | 52.3 | $1.50 / $9.00 | 1 of 4 categories | 57.2 | ||||
| 136 | GPT-5.6 Terra (low)openai/gpt-5.6-terra:low | OpenAI | 52.3 | $1.00 / $6.00 | 1 of 4 categories | 57.2 | |||
| 137 | gpt-oss-120b (high)openai/gpt-oss-120b:high | OpenAI | 52.3 | $0.03 / $0.17 | 1 of 4 categories | 57.2 | |||
| 138 | Claude Haiku 4.5 (high)anthropic/claude-haiku-4.5:high | Anthropic | 52.2 | $1.00 / $5.00 | 2 of 4 categories | 54.8 | 54.2 | ||
| 139 | Kimi K2 0905moonshotai/kimi-k2-0905 | MoonshotAI | 52.2 | $0.60 / $2.50 | 2 of 4 categories | 57.6 | 51.4 | ||
| 140 | o3openai/o3 | OpenAI | 52.1 | $2.00 / $8.00 | 4 of 4 categories | 48.2 | 60.6 | 57.5 | 46.8 |
| 141 | Mimo v2 Omnixiaomi/mimo-v2-omni | Xiaomi | 52.1 | — | 3 of 4 categories | 59.3 | 55.1 | 46.5 | |
| 142 | Qwen3 235B A22B Instruct 2507qwen/qwen3-235b-a22b-2507 | Qwen | 52.0 | $0.09 / $0.55 | 2 of 4 categories | 56.8 | 51.6 | ||
| 143 | GPT-5.6 Sol (high)openai/gpt-5.6-sol:high | OpenAI | 52.0 | $5.00 / $30.00 | 1 of 4 categories | 56.4 | |||
| 144 | Claude Opus 4.7 (xhigh)anthropic/claude-opus-4.7:xhigh | Anthropic | 52.0 | $5.00 / $25.00 | 1 of 4 categories | 56.3 | |||
| 145 | GLM 5V Turboz-ai/glm-5v-turbo | Z.ai | 51.9 | $1.20 / $4.00 | 3 of 4 categories | 56.6 | 57.1 | 46.4 | |
| 146 | LongCat Flash Chatmeituan/longcat-flash-chat | Meituan | 51.9 | — | 2 of 4 categories | 57.3 | 50.8 | ||
| 147 | o1 (medium)openai/o1:medium | OpenAI | 51.8 | $15.00 / $60.00 | 1 of 4 categories | 55.8 | |||
| 148 | Chatgpt 4oopenai/chatgpt-4o | OpenAI | 51.8 | — | 3 of 4 categories | 56.3 | 48.5 | 54.5 | |
| 149 | GPT-5.2 (low)openai/gpt-5.2:low | OpenAI | 51.8 | $1.75 / $14.00 | 1 of 4 categories | 55.7 | |||
| 150 | GPT-5.1-Codex (medium)openai/gpt-5.1-codex:medium | OpenAI | 51.7 | $1.25 / $10.00 | 2 of 4 categories | 53.7 | 53.6 | ||
| 151 | Qwen3.6 35B A3Bqwen/qwen3.6-35b-a3b | Qwen | 51.7 | $0.15 / $1.00 | 1 of 4 categories | 55.6 | |||
| 152 | Qwen3.7 Flashqwen/qwen3.7-flash | Qwen | 51.7 | $0.03 / $0.13 | 1 of 4 categories | 55.6 | |||
| 153 | Gemini 3.1 Flash Lite Previewgoogle/gemini-3.1-flash-lite-preview | 51.7 | $0.25 / $1.50 | 3 of 4 categories | 43.4 | 55.5 | 60.0 | ||
| 154 | GPT-5.2-Codexopenai/gpt-5.2-codex | OpenAI | 51.7 | $1.75 / $14.00 | 2 of 4 categories | 61.5 | 45.5 | ||
| 155 | GPT-5.1 (medium)openai/gpt-5.1:medium | OpenAI | 51.6 | $1.25 / $10.00 | 3 of 4 categories | 53.7 | 50.9 | 54.0 | |
| 156 | GPT-5 Mini (medium)openai/gpt-5-mini:medium | OpenAI | 51.6 | $0.25 / $2.00 | 3 of 4 categories | 48.9 | 52.7 | 57.0 | |
| 157 | DeepSeek V3.1 Terminus (thinking)deepseek/deepseek-v3.1-terminus:thinking | DeepSeek | 51.6 | $0.27 / $0.95 | 1 of 4 categories | 55.2 | |||
| 158 | o3 (high)openai/o3:high | OpenAI | 51.6 | $2.00 / $8.00 | 1 of 4 categories | 55.1 | |||
| 159 | Qwen3.5 Plusqwen/qwen3.5-plus | Qwen | 51.6 | $0.30 / $1.80 | 1 of 4 categories | 55.1 | |||
| 160 | MiniMax M3minimax/minimax-m3 | MiniMax | 51.6 | $0.30 / $1.20 | 4 of 4 categories | 38.2 | 64.1 | 53.8 | 53.7 |
| 161 | Ernie 5.0 Preview 1203baidu/ernie-5.0-preview-1203 | Baidu | 51.5 | — | 2 of 4 categories | 56.7 | 49.8 | ||
| 162 | Claude Sonnet 4.6 (32K)anthropic/claude-sonnet-4.6:32k | Anthropic | 51.5 | $3.00 / $15.00 | 1 of 4 categories | 54.7 | |||
| 163 | Kimi K2 Thinking Turbomoonshotai/kimi-k2-thinking-turbo | Moonshot AI | 51.4 | — | 2 of 4 categories | 49.4 | 56.6 | ||
| 164 | o4 Mini Highopenai/o4-mini-high | OpenAI | 51.2 | $1.10 / $4.40 | 1 of 4 categories | 53.9 | |||
| 165 | Claude Opus 4.8 (none)anthropic/claude-opus-4.8:none | Anthropic | 51.2 | $5.00 / $25.00 | 1 of 4 categories | 53.8 | |||
| 166 | GPT-5.4 (low)openai/gpt-5.4:low | OpenAI | 51.2 | $2.50 / $15.00 | 1 of 4 categories | 53.8 | |||
| 167 | GPT 5 Chatopenai/gpt-5-chat | OpenAI | 51.1 | — | 3 of 4 categories | 55.1 | 50.2 | 50.6 | |
| 168 | Grok 4.1 (thinking)x-ai/grok-4.1:thinking | xAI | 51.1 | — | 2 of 4 categories | 47.8 | 56.8 | ||
| 169 | DeepSeek V3.1 (thinking)deepseek/deepseek-chat-v3.1:thinking | DeepSeek | 51.0 | $0.25 / $0.95 | 2 of 4 categories | 53.5 | 50.6 | ||
| 170 | DeepSeek V4 Pro (xhigh)deepseek/deepseek-v4-pro:xhigh | DeepSeek | 51.0 | $1.168 / $2.336 | 1 of 4 categories | 53.3 | |||
| 171 | o3 (medium)openai/o3:medium | OpenAI | 50.9 | $2.00 / $8.00 | 2 of 4 categories | 51.2 | 52.9 | ||
| 172 | Claude Opus 4.5 (128K)anthropic/claude-opus-4.5:128k | Anthropic | 50.9 | $5.00 / $25.00 | 1 of 4 categories | 53.1 | |||
| 173 | GPT-5.3-Codexopenai/gpt-5.3-codex | OpenAI | 50.9 | $1.75 / $14.00 | 1 of 4 categories | 53.1 | |||
| 174 | Claude Sonnet 4.6 (medium)anthropic/claude-sonnet-4.6:medium | Anthropic | 50.7 | $3.00 / $15.00 | 1 of 4 categories | 52.6 | |||
| 175 | Gemini 3.6 Flash (low)google/gemini-3.6-flash:low | 50.7 | $1.50 / $7.50 | 1 of 4 categories | 52.6 | ||||
| 176 | Qwen3.5 397B A17B (none)qwen/qwen3.5-397b-a17b:none | Qwen | 50.7 | $0.50 / $3.60 | 1 of 4 categories | 52.6 | |||
| 177 | o1 (high)openai/o1:high | OpenAI | 50.7 | $15.00 / $60.00 | 1 of 4 categories | 52.6 | |||
| 178 | Qwen3 Next 80B A3B Instructqwen/qwen3-next-80b-a3b-instruct | Qwen | 50.7 | $0.10 / $1.10 | 2 of 4 categories | 51.9 | 51.2 | ||
| 179 | o3 Mini (medium)openai/o3-mini:medium | OpenAI | 50.6 | $1.10 / $4.40 | 1 of 4 categories | 52.3 | |||
| 180 | R1deepseek/deepseek-r1 | DeepSeek | 50.6 | $0.70 / $2.50 | 2 of 4 categories | 51.6 | 51.2 | ||
| 181 | DeepSeek V3.1deepseek/deepseek-chat-v3.1 | DeepSeek | 50.6 | $0.25 / $0.95 | 2 of 4 categories | 52.2 | 50.5 | ||
| 182 | Grok 4.20 0309 (reasoning)x-ai/grok-4.20-0309:reasoning | xAI | 50.5 | — | 1 of 4 categories | 51.9 | |||
| 183 | Inklingthinkingmachines/inkling | Thinking Machines | 50.5 | $0.95 / $4.05 | 3 of 4 categories | 32.3 | 57.9 | 62.8 | |
| 184 | Claude Sonnet 4.5anthropic/claude-sonnet-4.5 | Anthropic | 50.5 | $3.00 / $15.00 | 3 of 4 categories | 58.6 | 54.0 | 40.5 | |
| 185 | Qwen3 VL 235B A22B Instructqwen/qwen3-vl-235b-a22b-instruct | Qwen | 50.5 | $0.26 / $1.04 | 3 of 4 categories | 55.6 | 49.5 | 47.7 | |
| 186 | Claude Opus 4.5 (16K)anthropic/claude-opus-4.5:16k | Anthropic | 50.4 | $5.00 / $25.00 | 1 of 4 categories | 51.6 | |||
| 187 | R1 0528deepseek/deepseek-r1-0528 | DeepSeek | 50.4 | $0.50 / $2.15 | 2 of 4 categories | 55.5 | 46.4 | ||
| 188 | Step 3.5 Flashstepfun/step-3.5-flash | StepFun | 50.4 | $0.10 / $0.30 | 2 of 4 categories | 52.7 | 49.2 | ||
| 189 | Claude Opus 4 (thinking 16K)anthropic/claude-opus-4:thinking-16k | Anthropic | 50.4 | $15.00 / $75.00 | 3 of 4 categories | 62.1 | 52.1 | 38.1 | |
| 190 | Gemini 3.1 Flash Lite (high)google/gemini-3.1-flash-lite:high | 50.3 | $0.25 / $1.50 | 1 of 4 categories | 51.4 | ||||
| 191 | Gemini 3.5 Flash (minimal)google/gemini-3.5-flash:minimal | 50.3 | $1.50 / $9.00 | 1 of 4 categories | 51.4 | ||||
| 192 | Gemini 3.6 Flash (minimal)google/gemini-3.6-flash:minimal | 50.3 | $1.50 / $7.50 | 1 of 4 categories | 51.4 | ||||
| 193 | Qwen3.7 Plus (none)qwen/qwen3.7-plus:none | Qwen | 50.3 | $0.32 / $1.28 | 1 of 4 categories | 51.4 | |||
| 194 | DeepSeek V3.2 (thinking)deepseek/deepseek-v3.2:thinking | DeepSeek | 50.3 | $0.269 / $0.40 | 3 of 4 categories | 49.7 | 49.3 | 52.9 | |
| 195 | Hunyuan Hy3 Previewtencent/hunyuan-hy3-preview | Tencent | 50.3 | — | 2 of 4 categories | 48.4 | 53.1 | ||
| 196 | GPT-5.4 Mini (xhigh)openai/gpt-5.4-mini:xhigh | OpenAI | 50.1 | $0.75 / $4.50 | 1 of 4 categories | 50.7 | |||
| 197 | Gemini 3.5 Flash Litegoogle/gemini-3.5-flash-lite | 50.1 | $0.30 / $2.50 | 4 of 4 categories | 22.4 | 62.4 | 52.8 | 63.2 | |
| 198 | Claude Sonnet 4.6 (16K)anthropic/claude-sonnet-4.6:16k | Anthropic | 50.1 | $3.00 / $15.00 | 1 of 4 categories | 50.5 | |||
| 199 | GPT 4.5 Previewopenai/gpt-4.5-preview | OpenAI | 50.0 | — | 3 of 4 categories | 54.1 | 43.9 | 52.5 | |
| 200 | Qwen3.7 Flash (none)qwen/qwen3.7-flash:none | Qwen | 50.0 | $0.03 / $0.13 | 1 of 4 categories | 50.3 | |||
| 201 | GPT-5.1openai/gpt-5.1 | OpenAI | 49.9 | $1.25 / $10.00 | 3 of 4 categories | 49.6 | 52.4 | 47.9 | |
| 202 | GLM 4.7z-ai/glm-4.7 | Z.ai | 49.9 | $0.40 / $1.75 | 2 of 4 categories | 57.7 | 42.3 | ||
| 203 | Claude Sonnet 4.6 (high)anthropic/claude-sonnet-4.6:high | Anthropic | 49.8 | $3.00 / $15.00 | 1 of 4 categories | 49.7 | |||
| 204 | Qwen3.5-122B-A10Bqwen/qwen3.5-122b-a10b | Qwen | 49.7 | $0.29 / $2.40 | 3 of 4 categories | 48.4 | 52.5 | 48.1 | |
| 205 | Kimi K2 0711moonshotai/kimi-k2 | MoonshotAI | 49.6 | $0.57 / $2.30 | 2 of 4 categories | 53.5 | 45.5 | ||
| 206 | Claude Sonnet 4.5 (59K)anthropic/claude-sonnet-4.5:59k | Anthropic | 49.6 | $3.00 / $15.00 | 1 of 4 categories | 49.3 | |||
| 207 | Gemma 4 31B (minimal)google/gemma-4-31b-it:minimal | 49.6 | $0.10 / $0.34 | 1 of 4 categories | 49.0 | ||||
| 208 | Claude Sonnet 4 (thinking 32K)anthropic/claude-sonnet-4:thinking-32k | Anthropic | 49.5 | $3.00 / $15.00 | 3 of 4 categories | 57.1 | 47.9 | 43.0 | |
| 209 | DeepSeek V4 Flash 0423deepseek/deepseek-v4-flash | DeepSeek | 49.5 | $0.14 / $0.28 | 3 of 4 categories | 35.6 | 58.9 | 53.2 | |
| 210 | Gemini 3.1 Pro Preview (high)google/gemini-3.1-pro-preview:high | 49.5 | $2.00 / $12.00 | 2 of 4 categories | 36.4 | 61.8 | |||
| 211 | Gemini 2.5 Progoogle/gemini-2.5-pro | 49.5 | $1.25 / $10.00 | 4 of 4 categories | 43.0 | 42.3 | 48.0 | 63.8 | |
| 212 | Qwen3 235B A22B (nothinking)qwen/qwen3-235b-a22b:nothinking | Qwen | 49.4 | $0.455 / $1.82 | 2 of 4 categories | 51.8 | 46.4 | ||
| 213 | Claude Opus 4.1anthropic/claude-opus-4.1 | Anthropic | 49.3 | $15.00 / $75.00 | 2 of 4 categories | 53.2 | 44.4 | ||
| 214 | Claude Sonnet 4 (32K)anthropic/claude-sonnet-4:32k | Anthropic | 49.3 | $3.00 / $15.00 | 1 of 4 categories | 48.2 | |||
| 215 | Claude Sonnet 4.5 (16K)anthropic/claude-sonnet-4.5:16k | Anthropic | 49.3 | $3.00 / $15.00 | 1 of 4 categories | 48.2 | |||
| 216 | Claude Sonnet 4.6 (max)anthropic/claude-sonnet-4.6:max | Anthropic | 49.3 | $3.00 / $15.00 | 1 of 4 categories | 48.2 | |||
| 217 | Gemini 3.5 Flash Lite (high)google/gemini-3.5-flash-lite:high | 49.3 | $0.30 / $2.50 | 1 of 4 categories | 48.2 | ||||
| 218 | DeepSeek V3.1 Terminusdeepseek/deepseek-v3.1-terminus | DeepSeek | 49.2 | $0.27 / $0.95 | 2 of 4 categories | 50.7 | 46.5 | ||
| 219 | Qwen3 235B A22B Thinking 2507qwen/qwen3-235b-a22b-thinking-2507 | Qwen | 49.2 | $0.23 / $2.30 | 2 of 4 categories | 51.1 | 46.0 | ||
| 220 | Gemini 2.5 Pro Preview 06-05google/gemini-2.5-pro-preview | 49.2 | $1.25 / $10.00 | 1 of 4 categories | 47.9 | ||||
| 221 | MiniMax M2.5minimax/minimax-m2.5 | MiniMax | 49.2 | $0.22 / $0.90 | 2 of 4 categories | 50.2 | 46.8 | ||
| 222 | Claude Sonnet 4.5 (32K)anthropic/claude-sonnet-4.5:32k | Anthropic | 49.1 | $3.00 / $15.00 | 1 of 4 categories | 47.8 | |||
| 223 | Nemotron 3.5 Lightning 30B A3Bnvidia/nemotron-3.5-lightning-30b-a3b | NVIDIA | 49.1 | — | 1 of 4 categories | 47.8 | |||
| 224 | DeepSeek V3.2 Expdeepseek/deepseek-v3.2-exp | DeepSeek | 49.1 | $0.27 / $0.41 | 2 of 4 categories | 45.7 | 51.1 | ||
| 225 | Claude Haiku 4.5 (32K)anthropic/claude-haiku-4.5:32k | Anthropic | 49.1 | $1.00 / $5.00 | 1 of 4 categories | 47.6 | |||
| 226 | Claude Sonnet 5anthropic/claude-sonnet-5 | Anthropic | 49.0 | $2.00 / $10.00 | 1 of 4 categories | 47.5 | |||
| 227 | Gemma 4 31Bgoogle/gemma-4-31b-it | 49.0 | $0.10 / $0.34 | 4 of 4 categories | 23.0 | 55.0 | 61.1 | 55.3 | |
| 228 | Claude Opus 4.5 (32K)anthropic/claude-opus-4.5:32k | Anthropic | 49.0 | $5.00 / $25.00 | 1 of 4 categories | 47.3 | |||
| 229 | Kimi K2 Thinkingmoonshotai/kimi-k2-thinking | MoonshotAI | 49.0 | $0.60 / $2.50 | 3 of 4 categories | 51.1 | 51.9 | 42.2 | |
| 230 | Kimi K3 (low)moonshotai/kimi-k3:low | MoonshotAI | 48.9 | $3.00 / $15.00 | 1 of 4 categories | 47.2 | |||
| 231 | GPT-5.4 Nano (low)openai/gpt-5.4-nano:low | OpenAI | 48.9 | $0.20 / $1.25 | 1 of 4 categories | 47.2 | |||
| 232 | GPT-5.6 Sol (none)openai/gpt-5.6-sol:none | OpenAI | 48.9 | $5.00 / $30.00 | 1 of 4 categories | 47.2 | |||
| 233 | Qwen3.6 35B A3B (none)qwen/qwen3.6-35b-a3b:none | Qwen | 48.9 | $0.15 / $1.00 | 1 of 4 categories | 47.2 | |||
| 234 | Ernie 5.0 Preview 1022baidu/ernie-5.0-preview-1022 | Baidu | 48.9 | — | 2 of 4 categories | 48.9 | 46.9 | ||
| 235 | GPT-5.1 (low)openai/gpt-5.1:low | OpenAI | 48.8 | $1.25 / $10.00 | 1 of 4 categories | 46.9 | |||
| 236 | Devstral Small 2512mistralai/devstral-small-2512 | Mistral AI | 48.8 | — | 2 of 4 categories | 47.4 | 48.1 | ||
| 237 | GPT-5.6 Luna (low)openai/gpt-5.6-luna:low | OpenAI | 48.7 | $0.10 / $0.60 | 1 of 4 categories | 46.4 | |||
| 238 | Qwen3.6 27B (none)qwen/qwen3.6-27b:none | Qwen | 48.7 | $0.60 / $3.60 | 1 of 4 categories | 46.4 | |||
| 239 | Qwen3 30B A3B Instruct 2507qwen/qwen3-30b-a3b-instruct-2507 | Qwen | 48.7 | $0.0482 / $0.1931 | 2 of 4 categories | 50.8 | 44.2 | ||
| 240 | GPT-5 Mini (high)openai/gpt-5-mini:high | OpenAI | 48.6 | $0.25 / $2.00 | 3 of 4 categories | 48.6 | 57.5 | 37.6 | |
| 241 | Qwen3 Coder 30B A3B Instructqwen/qwen3-coder-30b-a3b-instruct | Qwen | 48.6 | $0.07 / $0.28 | 1 of 4 categories | 46.3 | |||
| 242 | Grok 3 Mini Beta (low)x-ai/grok-3-mini-beta:low | xAI | 48.5 | — | 1 of 4 categories | 45.8 | |||
| 243 | MiniMax M2.1minimax/minimax-m2.1 | MiniMax | 48.4 | $0.30 / $1.20 | 2 of 4 categories | 48.2 | 45.9 | ||
| 244 | GLM 4.5 Airz-ai/glm-4.5-air | Z.ai | 48.4 | $0.13 / $0.85 | 2 of 4 categories | 48.2 | 45.8 | ||
| 245 | Devstral Small 2505mistralai/devstral-small-2505 | Mistral AI | 48.4 | — | 1 of 4 categories | 45.5 | |||
| 246 | Laguna M.1poolside/laguna-m.1 | Poolside | 48.4 | — | 1 of 4 categories | 45.5 | |||
| 247 | Qwen3.6 Flashqwen/qwen3.6-flash | Qwen | 48.4 | $0.1875 / $1.125 | 1 of 4 categories | 45.4 | |||
| 248 | Qwen3 32Bqwen/qwen3-32b | Qwen | 48.4 | $0.08 / $0.28 | 2 of 4 categories | 46.3 | 47.5 | ||
| 249 | Qwen3 Next 80B A3B Thinkingqwen/qwen3-next-80b-a3b-thinking | Qwen | 48.3 | $0.15 / $1.20 | 2 of 4 categories | 47.6 | 46.1 | ||
| 250 | Hunyuan T1tencent/hunyuan-t1 | Tencent | 48.3 | — | 2 of 4 categories | 45.7 | 47.8 | ||
| 251 | GPT-5.4 Nano (high)openai/gpt-5.4-nano:high | OpenAI | 48.3 | $0.20 / $1.25 | 3 of 4 categories | 54.5 | 52.6 | 34.7 | |
| 252 | GPT-5.2 (none)openai/gpt-5.2:none | OpenAI | 48.3 | $1.75 / $14.00 | 1 of 4 categories | 45.2 | |||
| 253 | Qwen3.5-27Bqwen/qwen3.5-27b | Qwen | 48.3 | $0.195 / $1.56 | 3 of 4 categories | 46.8 | 54.1 | 40.8 | |
| 254 | o4 Mini (medium)openai/o4-mini:medium | OpenAI | 48.2 | $1.10 / $4.40 | 1 of 4 categories | 44.9 | |||
| 255 | Claude 3.7 Sonnet (32K)anthropic/claude-3-7-sonnet:32k | Anthropic | 48.1 | — | 1 of 4 categories | 44.8 | |||
| 256 | Claude Opus 4 (16K)anthropic/claude-opus-4:16k | Anthropic | 48.1 | $15.00 / $75.00 | 1 of 4 categories | 44.8 | |||
| 257 | Gemini 3.5 Flash Lite (low)google/gemini-3.5-flash-lite:low | 48.1 | $0.30 / $2.50 | 1 of 4 categories | 44.8 | ||||
| 258 | Trinity Large Previewarcee-ai/trinity-large-preview | Arcee AI | 48.1 | — | 2 of 4 categories | 51.2 | 41.6 | ||
| 259 | o3 Mini Highopenai/o3-mini-high | OpenAI | 48.1 | $1.10 / $4.40 | 2 of 4 categories | 49.7 | 42.9 | ||
| 260 | GPT-5.1-Codexopenai/gpt-5.1-codex | OpenAI | 48.0 | $1.25 / $10.00 | 1 of 4 categories | 44.3 | |||
| 261 | GPT-5.4 (none)openai/gpt-5.4:none | OpenAI | 48.0 | $2.50 / $15.00 | 1 of 4 categories | 44.3 | |||
| 262 | GPT-5.5 (none)openai/gpt-5.5:none | OpenAI | 48.0 | $5.00 / $30.00 | 1 of 4 categories | 44.3 | |||
| 263 | o1openai/o1 | OpenAI | 47.9 | $15.00 / $60.00 | 3 of 4 categories | 48.9 | 44.0 | 47.2 | |
| 264 | Nova Premier 1.0amazon/nova-premier-v1 | Amazon | 47.9 | $2.50 / $12.50 | 1 of 4 categories | 44.2 | |||
| 265 | o4 Mini (low)openai/o4-mini:low | OpenAI | 47.9 | $1.10 / $4.40 | 1 of 4 categories | 44.0 | |||
| 266 | Claude Opus 4.1 (27K)anthropic/claude-opus-4.1:27k | Anthropic | 47.8 | $15.00 / $75.00 | 1 of 4 categories | 43.9 | |||
| 267 | Claude Opus 4anthropic/claude-opus-4 | Anthropic | 47.8 | $15.00 / $75.00 | 4 of 4 categories | 55.6 | 56.5 | 38.5 | 36.7 |
| 268 | GPT-5 Mini (minimal)openai/gpt-5-mini:minimal | OpenAI | 47.8 | $0.25 / $2.00 | 1 of 4 categories | 43.8 | |||
| 269 | INTELLECT-3prime-intellect/intellect-3 | Prime Intellect | 47.8 | — | 2 of 4 categories | 46.7 | 44.8 | ||
| 270 | gpt-oss-20b (high)openai/gpt-oss-20b:high | OpenAI | 47.7 | $0.03 / $0.13 | 1 of 4 categories | 43.5 | |||
| 271 | o3 (low)openai/o3:low | OpenAI | 47.7 | $2.00 / $8.00 | 1 of 4 categories | 43.5 | |||
| 272 | Grok 4.3x-ai/grok-4.3 | SpaceXAI | 47.7 | $1.25 / $2.50 | 4 of 4 categories | 27.7 | 51.6 | 51.8 | 55.6 |
| 273 | Llama 3.3 Nemotron Super 49B v1.5nvidia/llama-3.3-nemotron-super-49b-v1.5 | NVIDIA | 47.7 | — | 2 of 4 categories | 46.0 | 45.2 | ||
| 274 | DeepSeek V3.2deepseek/deepseek-v3.2 | DeepSeek | 47.7 | $0.269 / $0.40 | 2 of 4 categories | 39.8 | 51.3 | ||
| 275 | Ernie 5.0 Preview 1220baidu/ernie-5.0-preview-1220 | Baidu | 47.7 | — | 1 of 4 categories | 43.4 | |||
| 276 | GLM 4.7 Flashz-ai/glm-4.7-flash | Z.ai | 47.6 | $0.06 / $0.40 | 2 of 4 categories | 48.1 | 42.8 | ||
| 277 | Claude 3.7 Sonnet (16K)anthropic/claude-3-7-sonnet:16k | Anthropic | 47.6 | — | 1 of 4 categories | 43.1 | |||
| 278 | Claude Sonnet 4anthropic/claude-sonnet-4 | Anthropic | 47.6 | $3.00 / $15.00 | 4 of 4 categories | 51.9 | 63.2 | 35.7 | 35.1 |
| 279 | Qwen3 VL 235B A22B Thinkingqwen/qwen3-vl-235b-a22b-thinking | Qwen | 47.6 | $0.40 / $4.00 | 3 of 4 categories | 53.1 | 48.4 | 36.7 | |
| 280 | Claude Sonnet 4 (16K)anthropic/claude-sonnet-4:16k | Anthropic | 47.5 | $3.00 / $15.00 | 1 of 4 categories | 43.0 | |||
| 281 | GPT-5.6 Terra (none)openai/gpt-5.6-terra:none | OpenAI | 47.5 | $1.00 / $6.00 | 1 of 4 categories | 43.0 | |||
| 282 | o1 (low)openai/o1:low | OpenAI | 47.5 | $15.00 / $60.00 | 1 of 4 categories | 43.0 | |||
| 283 | MiniMax M1minimax/minimax-m1 | MiniMax | 47.5 | $0.55 / $2.20 | 2 of 4 categories | 47.2 | 43.2 | ||
| 284 | Nemotron 3 Supernvidia/nemotron-3-super-120b-a12b | NVIDIA | 47.5 | $0.085 / $0.40 | 2 of 4 categories | 46.4 | 43.9 | ||
| 285 | Laguna XS.2poolside/laguna-xs.2 | Poolside | 47.5 | — | 1 of 4 categories | 42.8 | |||
| 286 | DeepSeek V4 Flash 0423 (xhigh)deepseek/deepseek-v4-flash:xhigh | DeepSeek | 47.4 | $0.14 / $0.28 | 1 of 4 categories | 42.7 | |||
| 287 | Gemini 3.5 Flash Lite (minimal)google/gemini-3.5-flash-lite:minimal | 47.4 | $0.30 / $2.50 | 1 of 4 categories | 42.5 | ||||
| 288 | Devstral Small 2507mistralai/devstral-small-2507 | Mistral AI | 47.4 | — | 1 of 4 categories | 42.5 | |||
| 289 | Mercuryinception/mercury | Inception | 47.3 | — | 1 of 4 categories | 42.3 | |||
| 290 | O1 Mini (high)openai/o1-mini:high | OpenAI | 47.3 | — | 1 of 4 categories | 42.2 | |||
| 291 | Llama 3.1 Nemotron Ultra 253B v1nvidia/llama-3.1-nemotron-ultra-253b-v1 | NVIDIA | 47.3 | — | 2 of 4 categories | 45.0 | 44.4 | ||
| 292 | o4 Miniopenai/o4-mini | OpenAI | 47.3 | $1.10 / $4.40 | 4 of 4 categories | 41.5 | 48.9 | 50.9 | 42.5 |
| 293 | Grok 3 Betax-ai/grok-3-beta | xAI | 47.3 | — | 2 of 4 categories | 51.3 | 38.0 | ||
| 294 | Qwen VL (max)qwen/qwen-vl:max | Qwen | 47.2 | — | 1 of 4 categories | 42.0 | |||
| 295 | Qwen3 Coder 480B A35b Instructqwen/qwen3-coder-480b-a35b-instruct | Qwen | 47.2 | — | 3 of 4 categories | 45.6 | 47.0 | 43.8 | |
| 296 | o3 Miniopenai/o3-mini | OpenAI | 47.2 | $1.10 / $4.40 | 2 of 4 categories | 44.5 | 44.6 | ||
| 297 | Llama 3.3 Nemotron Super 49B v1nvidia/llama-3.3-nemotron-super-49b-v1 | NVIDIA | 47.2 | — | 1 of 4 categories | 41.9 | |||
| 298 | Mimo v2 Flashxiaomi/mimo-v2-flash | Xiaomi | 47.1 | — | 2 of 4 categories | 44.7 | 44.1 | ||
| 299 | DeepSeek V4 Pro (none)deepseek/deepseek-v4-pro:none | DeepSeek | 47.1 | $1.168 / $2.336 | 1 of 4 categories | 41.6 | |||
| 300 | GPT-5 Nano (low)openai/gpt-5-nano:low | OpenAI | 47.1 | $0.05 / $0.40 | 1 of 4 categories | 41.6 | |||
| 301 | GPT-5 (minimal)openai/gpt-5:minimal | OpenAI | 47.1 | $1.25 / $10.00 | 1 of 4 categories | 41.6 | |||
| 302 | GPT-5.4 Nano (none)openai/gpt-5.4-nano:none | OpenAI | 47.1 | $0.20 / $1.25 | 1 of 4 categories | 41.6 | |||
| 303 | Claude Opus 4 (27K)anthropic/claude-opus-4:27k | Anthropic | 47.0 | $15.00 / $75.00 | 1 of 4 categories | 41.5 | |||
| 304 | Claude 3.7 Sonnet (thinking 32K)anthropic/claude-3-7-sonnet:thinking-32k | Anthropic | 46.9 | — | 3 of 4 categories | 52.9 | 45.1 | 37.1 | |
| 305 | Qwen 2.5 (max)qwen/qwen-2.5:max | Qwen | 46.9 | — | 2 of 4 categories | 45.9 | 42.2 | ||
| 306 | Qwen3.5-35B-A3Bqwen/qwen3.5-35b-a3b | Qwen | 46.9 | $0.25 / $1.25 | 2 of 4 categories | 40.4 | 47.6 | ||
| 307 | Grok 4 Fast (reasoning)x-ai/grok-4-fast:reasoning | xAI | 46.9 | — | 2 of 4 categories | 37.9 | 49.9 | ||
| 308 | Nemotron 3 Ultranvidia/nemotron-3-ultra-550b-a55b | NVIDIA | 46.9 | $0.60 / $3.60 | 3 of 4 categories | 20.2 | 57.8 | 56.7 | |
| 309 | KAT-Coder-Pro V1kwaipilot/kat-coder-pro-v1 | Kwaipilot | 46.9 | — | 1 of 4 categories | 40.9 | |||
| 310 | Ling Flash 2.0inclusionai/ling-flash-2.0 | inclusionAI | 46.8 | — | 2 of 4 categories | 46.8 | 40.8 | ||
| 311 | Gemini 3.1 Flash Lite (low)google/gemini-3.1-flash-lite:low | 46.8 | $0.25 / $1.50 | 1 of 4 categories | 40.7 | ||||
| 312 | o3 Mini (low)openai/o3-mini:low | OpenAI | 46.8 | $1.10 / $4.40 | 1 of 4 categories | 40.7 | |||
| 313 | Grok 3 Mini Beta (high)x-ai/grok-3-mini-beta:high | xAI | 46.8 | — | 2 of 4 categories | 44.6 | 42.7 | ||
| 314 | Grok 4 0709x-ai/grok-4-0709 | xAI | 46.6 | — | 3 of 4 categories | 49.8 | 48.0 | 35.6 | |
| 315 | Grok 3 Mini Betax-ai/grok-3-mini-beta | xAI | 46.6 | — | 2 of 4 categories | 43.9 | 42.9 | ||
| 316 | GPT-5.6 Luna (none)openai/gpt-5.6-luna:none | OpenAI | 46.6 | $0.10 / $0.60 | 1 of 4 categories | 40.2 | |||
| 317 | GPT-5.1-Codex-Miniopenai/gpt-5.1-codex-mini | OpenAI | 46.6 | $0.25 / $2.00 | 1 of 4 categories | 40.0 | |||
| 318 | Mistral Large 3mistralai/mistral-large-3 | Mistral AI | 46.5 | — | 3 of 4 categories | 43.9 | 48.6 | 40.4 | |
| 319 | Claude 3.7 Sonnet (64K)anthropic/claude-3-7-sonnet:64k | Anthropic | 46.5 | — | 1 of 4 categories | 39.8 | |||
| 320 | O1 Mini (medium)openai/o1-mini:medium | OpenAI | 46.5 | — | 1 of 4 categories | 39.7 | |||
| 321 | GLM 4.6z-ai/glm-4.6 | Z.ai | 46.5 | $0.50 / $2.00 | 3 of 4 categories | 45.6 | 44.1 | 43.0 | |
| 322 | MiniMax M2.7minimax/minimax-m2.7 | MiniMax | 46.4 | $0.30 / $1.20 | 3 of 4 categories | 25.2 | 55.0 | 52.2 | |
| 323 | Gemini 3.1 Flash Lite (minimal)google/gemini-3.1-flash-lite:minimal | 46.4 | $0.25 / $1.50 | 1 of 4 categories | 39.5 | ||||
| 324 | Qwen 2.5qwen/qwen-2.5 | Qwen | 46.4 | — | 1 of 4 categories | 39.6 | |||
| 325 | Qwen3 235B A22Bqwen/qwen3-235b-a22b | Qwen | 46.4 | $0.455 / $1.82 | 2 of 4 categories | 49.2 | 36.7 | ||
| 326 | QwQ 32Bqwen/qwq-32b | Qwen | 46.4 | — | 2 of 4 categories | 43.4 | 42.5 | ||
| 327 | O1 Miniopenai/o1-mini | OpenAI | 46.4 | — | 2 of 4 categories | 44.1 | 41.8 | ||
| 328 | Hunyuan TurboStencent/hunyuan-turbos | Tencent | 46.3 | — | 2 of 4 categories | 45.3 | 40.2 | ||
| 329 | Kimi K2 Instructmoonshotai/kimi-k2-instruct | Moonshot AI | 46.3 | — | 2 of 4 categories | 40.8 | 44.7 | ||
| 330 | Grok 4.1 Fast (reasoning)x-ai/grok-4-1-fast:reasoning | xAI | 46.2 | — | 3 of 4 categories | 43.7 | 51.5 | 36.4 | |
| 331 | GPT-5 Nano (minimal)openai/gpt-5-nano:minimal | OpenAI | 46.2 | $0.05 / $0.40 | 1 of 4 categories | 38.9 | |||
| 332 | Claude Haiku 4.5anthropic/claude-haiku-4.5 | Anthropic | 46.1 | $1.00 / $5.00 | 2 of 4 categories | 42.5 | 42.3 | ||
| 333 | Nova 2 Liteamazon/nova-2-lite-v1 | Amazon | 46.1 | $0.30 / $2.50 | 2 of 4 categories | 45.5 | 39.4 | ||
| 334 | Ring Flash 2.0inclusionai/ring-flash-2.0 | inclusionAI | 46.1 | — | 2 of 4 categories | 44.9 | 39.9 | ||
| 335 | Qwen3 30B A3Bqwen/qwen3-30b-a3b | Qwen | 46.1 | $0.12 / $0.50 | 2 of 4 categories | 43.8 | 40.9 | ||
| 336 | GPT-5 Nano (medium)openai/gpt-5-nano:medium | OpenAI | 46.1 | $0.05 / $0.40 | 3 of 4 categories | 39.3 | 42.1 | 49.4 | |
| 337 | Mimo v2 Flash (thinking)xiaomi/mimo-v2-flash:thinking | Xiaomi | 46.0 | — | 2 of 4 categories | 40.9 | 43.6 | ||
| 338 | Qwen2.5 VL 72B Instructqwen/qwen2.5-vl-72b-instruct | Qwen | 46.0 | — | 1 of 4 categories | 38.5 | |||
| 339 | MiniMax M2minimax/minimax-m2 | MiniMax | 45.9 | $0.255 / $1.02 | 3 of 4 categories | 50.4 | 38.4 | 41.2 | |
| 340 | Qwen2.5 VL 32B Instructqwen/qwen2.5-vl-32b-instruct | Qwen | 45.9 | — | 1 of 4 categories | 37.9 | |||
| 341 | GLM 5.2 (none)z-ai/glm-5.2:none | Z.ai | 45.8 | $0.63 / $1.98 | 1 of 4 categories | 37.8 | |||
| 342 | Claude Sonnet 4 (59K)anthropic/claude-sonnet-4:59k | Anthropic | 45.8 | $3.00 / $15.00 | 1 of 4 categories | 37.8 | |||
| 343 | GPT-5.4 Mini (none)openai/gpt-5.4-mini:none | OpenAI | 45.7 | $0.75 / $4.50 | 1 of 4 categories | 37.5 | |||
| 344 | Qwen3.5-Flashqwen/qwen3.5-flash-02-23 | Qwen | 45.6 | $0.065 / $0.26 | 2 of 4 categories | 39.8 | 43.1 | ||
| 345 | DeepSeek V3deepseek/deepseek-chat | DeepSeek | 45.6 | $0.2574 / $1.0287 | 2 of 4 categories | 49.3 | 33.3 | ||
| 346 | Command A (03-2025)cohere/command-a-03-2025 | Cohere | 45.6 | — | 2 of 4 categories | 44.5 | 38.1 | ||
| 347 | Grok Code Fast 1x-ai/grok-code-fast-1 | xAI | 45.6 | — | 1 of 4 categories | 37.0 | |||
| 348 | Trinity Large Thinkingarcee-ai/trinity-large-thinking | Arcee AI | 45.5 | $0.22 / $0.85 | 2 of 4 categories | 37.6 | 44.9 | ||
| 349 | GPT-5 Miniopenai/gpt-5-mini | OpenAI | 45.5 | $0.25 / $2.00 | 2 of 4 categories | 46.7 | 35.8 | ||
| 350 | Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b | NVIDIA | 45.5 | $0.05 / $0.20 | 2 of 4 categories | 41.8 | 40.5 | ||
| 351 | gpt-oss-20bopenai/gpt-oss-20b | OpenAI | 45.4 | $0.03 / $0.13 | 2 of 4 categories | 42.6 | 39.5 | ||
| 352 | DeepSeek V3 0324deepseek/deepseek-chat-v3-0324 | DeepSeek | 45.4 | $0.27 / $1.12 | 2 of 4 categories | 48.3 | 33.7 | ||
| 353 | Hunyuan Vision 1.5 (thinking)tencent/hunyuan-vision-1.5:thinking | Tencent | 45.4 | — | 2 of 4 categories | 50.5 | 31.3 | ||
| 354 | Devstral Medium 2507mistralai/devstral-medium-2507 | Mistral AI | 45.3 | — | 1 of 4 categories | 36.4 | |||
| 355 | GPT-4oopenai/gpt-4o | OpenAI | 45.3 | $2.50 / $10.00 | 1 of 4 categories | 36.4 | |||
| 356 | Grok 4.3 (high)x-ai/grok-4.3:high | SpaceXAI | 45.3 | $1.25 / $2.50 | 2 of 4 categories | 30.4 | 51.2 | ||
| 357 | Claude Opus 4.8 (medium)anthropic/claude-opus-4.8:medium | Anthropic | 45.2 | $5.00 / $25.00 | 1 of 4 categories | 35.9 | |||
| 358 | Gemini 2.5 Flashgoogle/gemini-2.5-flash | 45.1 | $0.30 / $2.50 | 4 of 4 categories | 38.6 | 39.6 | 44.3 | 48.4 | |
| 359 | OLMo 3.1 32B Instructallenai/olmo-3.1-32b-instruct | Allen Institute for AI | 45.0 | — | 2 of 4 categories | 43.0 | 37.5 | ||
| 360 | OLMo 3 32B Thinkallenai/olmo-3-32b-think | Allen Institute for AI | 45.0 | — | 2 of 4 categories | 42.0 | 38.4 | ||
| 361 | Magistral Medium 2506mistralai/magistral-medium-2506 | Mistral AI | 44.9 | — | 2 of 4 categories | 44.2 | 35.9 | ||
| 362 | Claude Opus 4.1 (16K)anthropic/claude-opus-4.1:16k | Anthropic | 44.9 | $15.00 / $75.00 | 1 of 4 categories | 35.1 | |||
| 363 | GLM 4.5z-ai/glm-4.5 | Z.ai | 44.9 | $0.60 / $2.20 | 3 of 4 categories | 44.5 | 47.7 | 32.7 | |
| 364 | Claude 3.7 Sonnetanthropic/claude-3-7-sonnet | Anthropic | 44.9 | — | 4 of 4 categories | 42.3 | 59.6 | 33.9 | 33.9 |
| 365 | Devstral 2mistralai/devstral-2 | Mistral AI | 44.9 | — | 2 of 4 categories | 43.7 | 36.1 | ||
| 366 | GPT-5.1 (none)openai/gpt-5.1:none | OpenAI | 44.7 | $1.25 / $10.00 | 1 of 4 categories | 34.6 | |||
| 367 | Mercury 2inception/mercury-2 | Inception | 44.7 | $0.25 / $0.75 | 1 of 4 categories | 34.6 | |||
| 368 | Mistral Medium 2508mistralai/mistral-medium-2508 | Mistral AI | 44.6 | — | 3 of 4 categories | 53.3 | 47.2 | 23.0 | |
| 369 | Mistral Medium 3.5mistralai/mistral-medium-3-5 | Mistral | 44.4 | $1.50 / $7.50 | 4 of 4 categories | 25.2 | 47.1 | 54.6 | 39.8 |
| 370 | GPT-4.1openai/gpt-4.1 | OpenAI | 44.3 | $2.00 / $8.00 | 4 of 4 categories | 40.0 | 46.3 | 35.9 | 44.2 |
| 371 | Claude Opus 4.1 (32K)anthropic/claude-opus-4.1:32k | Anthropic | 44.3 | $15.00 / $75.00 | 1 of 4 categories | 33.3 | |||
| 372 | Gemini 1.5 Pro 002google/gemini-1.5-pro-002 | 44.3 | — | 3 of 4 categories | 41.1 | 35.7 | 44.9 | ||
| 373 | Gemma 3 12Bgoogle/gemma-3-12b-it | 44.2 | $0.05 / $0.15 | 2 of 4 categories | 38.5 | 38.8 | |||
| 374 | Qwen (max)qwen/qwen:max | Qwen | 44.1 | — | 1 of 4 categories | 32.6 | |||
| 375 | Mistral Nemomistralai/mistral-nemo | Mistral | 44.1 | $0.019 / $0.03 | 1 of 4 categories | 32.6 | |||
| 376 | Gemini 2.5 Flash Lite (thinking)google/gemini-2.5-flash-lite:thinking | 43.9 | $0.10 / $0.40 | 3 of 4 categories | 43.1 | 42.6 | 33.9 | ||
| 377 | OLMo 3.1 32B Thinkallenai/olmo-3.1-32b-think | Allen Institute for AI | 43.8 | — | 2 of 4 categories | 38.9 | 36.6 | ||
| 378 | Gemini 2.5 Flash Lite (nothinking)google/gemini-2.5-flash-lite:nothinking | 43.8 | $0.10 / $0.40 | 3 of 4 categories | 45.6 | 42.4 | 31.2 | ||
| 379 | GLM 4.6Vz-ai/glm-4.6v | Z.ai | 43.8 | $0.30 / $0.90 | 2 of 4 categories | 47.5 | 27.8 | ||
| 380 | gpt-oss-120bopenai/gpt-oss-120b | OpenAI | 43.7 | $0.03 / $0.17 | 3 of 4 categories | 37.8 | 36.7 | 44.5 | |
| 381 | Grok 2 1212x-ai/grok-2-1212 | xAI | 43.7 | — | 1 of 4 categories | 31.5 | |||
| 382 | GLM 5.2 (high)z-ai/glm-5.2:high | Z.ai | 43.6 | $0.63 / $1.98 | 1 of 4 categories | 31.1 | |||
| 383 | Gemini 2.0 Flash Lite Preview 02 05google/gemini-2.0-flash-lite-preview-02-05 | 43.5 | — | 3 of 4 categories | 39.3 | 39.2 | 39.6 | ||
| 384 | GPT-4.1 Miniopenai/gpt-4.1-mini | OpenAI | 43.2 | $0.40 / $1.60 | 4 of 4 categories | 37.1 | 40.0 | 42.4 | 40.2 |
| 385 | Gemma 3n E4Bgoogle/gemma-3n-e4b-it | 43.0 | — | 2 of 4 categories | 37.9 | 34.5 | |||
| 386 | Magistral Small 2506mistralai/magistral-small-2506 | Mistral AI | 43.0 | — | 1 of 4 categories | 29.3 | |||
| 387 | Grok Build 0.1x-ai/grok-build-0.1 | SpaceXAI | 42.9 | $1.00 / $2.00 | 1 of 4 categories | 29.0 | |||
| 388 | Solar Pro 4upstage/solar-pro4 | Upstage | 42.9 | $0.03 / $0.12 | 2 of 4 categories | 23.6 | 48.3 | ||
| 389 | Qwen2.5 72B Instructqwen/qwen-2.5-72b-instruct | Qwen | 42.9 | $0.36 / $0.40 | 2 of 4 categories | 40.8 | 31.1 | ||
| 390 | GPT-4o (2024-05-13)openai/gpt-4o-2024-05-13 | OpenAI | 42.7 | $5.00 / $15.00 | 3 of 4 categories | 41.1 | 29.1 | 43.5 | |
| 391 | Gemma 3 4Bgoogle/gemma-3-4b-it | 42.7 | — | 2 of 4 categories | 36.8 | 34.2 | |||
| 392 | GLM 4.5Vz-ai/glm-4.5v | Z.ai | 42.6 | $0.60 / $1.80 | 3 of 4 categories | 46.1 | 41.5 | 25.9 | |
| 393 | GPT-5 Nano (high)openai/gpt-5-nano:high | OpenAI | 42.6 | $0.05 / $0.40 | 3 of 4 categories | 43.3 | 44.2 | 26.1 | |
| 394 | Command R+ (08-2024)cohere/command-r-plus-08-2024 | Cohere | 42.6 | $2.50 / $10.00 | 2 of 4 categories | 37.2 | 33.6 | ||
| 395 | SWE Llamaprinceton-nlp/swe-llama | Princeton NLP | 42.6 | — | 1 of 4 categories | 28.1 | |||
| 396 | Amazon Nova Micro v1.0amazon/amazon-nova-micro-v1.0 | Amazon | 42.5 | — | 2 of 4 categories | 37.5 | 33.1 | ||
| 397 | Step 3stepfun/step-3 | StepFun | 42.5 | — | 3 of 4 categories | 46.6 | 41.9 | 24.4 | |
| 398 | OLMo 2 0325 32B Instructallenai/olmo-2-0325-32b-instruct | Allen Institute for AI | 42.5 | — | 2 of 4 categories | 37.1 | 33.2 | ||
| 399 | Command R (08-2024)cohere/command-r-08-2024 | Cohere | 42.4 | $0.15 / $0.60 | 2 of 4 categories | 37.4 | 32.8 | ||
| 400 | Granite 4.1 8Bibm-granite/granite-4.1-8b | IBM | 42.4 | $0.05 / $0.10 | 2 of 4 categories | 31.2 | 38.9 | ||
| 401 | Claude Opus 4.7 (medium)anthropic/claude-opus-4.7:medium | Anthropic | 42.3 | $5.00 / $25.00 | 1 of 4 categories | 27.3 | |||
| 402 | GPT 4 1106 Previewopenai/gpt-4-1106-preview | OpenAI | 42.3 | — | 2 of 4 categories | 38.4 | 31.2 | ||
| 403 | QwQ 32B Previewqwen/qwq-32b-preview | Qwen | 42.2 | — | 2 of 4 categories | 36.4 | 32.9 | ||
| 404 | SWE Llama 13Bprinceton-nlp/swe-llama-13b | Princeton NLP | 42.0 | — | 1 of 4 categories | 26.5 | |||
| 405 | Mistral Large 2407mistralai/mistral-large-2407 | Mistral | 41.9 | $2.00 / $6.00 | 2 of 4 categories | 40.5 | 27.3 | ||
| 406 | Amazon Nova Pro v1.0amazon/amazon-nova-pro-v1.0 | Amazon | 41.9 | — | 3 of 4 categories | 39.4 | 34.8 | 35.4 | |
| 407 | GPT-4.1 Nanoopenai/gpt-4.1-nano | OpenAI | 41.8 | $0.10 / $0.40 | 3 of 4 categories | 42.9 | 29.8 | 36.5 | |
| 408 | Claude 3.5 Sonnetanthropic/claude-3-5-sonnet | Anthropic | 41.5 | — | 3 of 4 categories | 52.3 | 26.7 | 29.2 | |
| 409 | Amazon Nova Lite v1.0amazon/amazon-nova-lite-v1.0 | Amazon | 41.3 | — | 3 of 4 categories | 37.8 | 33.9 | 35.1 | |
| 410 | Llama 3.3 70B Instructmeta-llama/llama-3.3-70b-instruct | Meta | 41.3 | $0.10 / $0.32 | 2 of 4 categories | 39.6 | 25.9 | ||
| 411 | Mistral Large 2411mistralai/mistral-large-2411 | Mistral AI | 41.1 | — | 2 of 4 categories | 39.7 | 24.9 | ||
| 412 | Mistral Small 2506mistralai/mistral-small-2506 | Mistral AI | 41.0 | — | 3 of 4 categories | 47.0 | 39.6 | 19.0 | |
| 413 | GPT-4o-mini (2024-07-18)openai/gpt-4o-mini-2024-07-18 | OpenAI | 41.0 | $0.15 / $0.60 | 3 of 4 categories | 40.1 | 28.5 | 36.8 | |
| 414 | GPT-4o (2024-11-20)openai/gpt-4o-2024-11-20 | OpenAI | 41.0 | $2.50 / $10.00 | 3 of 4 categories | 36.3 | 41.7 | 27.2 | |
| 415 | GPT-4 Turboopenai/gpt-4-turbo | OpenAI | 41.0 | $10.00 / $30.00 | 3 of 4 categories | 40.0 | 27.8 | 37.4 | |
| 416 | Gemini 1.5 Pro 001google/gemini-1.5-pro-001 | 40.9 | — | 3 of 4 categories | 39.8 | 26.7 | 38.2 | ||
| 417 | Gemini 1.5 Flash 002google/gemini-1.5-flash-002 | 40.8 | — | 3 of 4 categories | 38.3 | 26.1 | 40.2 | ||
| 418 | Mixtral 8x22B Instructmistralai/mixtral-8x22b-instruct | Mistral | 40.8 | $2.00 / $6.00 | 2 of 4 categories | 37.0 | 26.8 | ||
| 419 | Mistral Small 24B Instruct 2501mistralai/mistral-small-24b-instruct-2501 | Mistral AI | 40.8 | — | 2 of 4 categories | 38.2 | 25.3 | ||
| 420 | GPT-4o (2024-08-06)openai/gpt-4o-2024-08-06 | OpenAI | 40.6 | $2.50 / $10.00 | 3 of 4 categories | 39.6 | 26.4 | 37.6 | |
| 421 | Molmo 2 8Ballenai/molmo-2-8b | Allen Institute for AI | 40.6 | — | 1 of 4 categories | 22.3 | |||
| 422 | Mistral Medium 2505mistralai/mistral-medium-2505 | Mistral AI | 40.5 | — | 3 of 4 categories | 49.4 | 33.6 | 20.0 | |
| 423 | GPT 3.5openai/gpt-3.5 | OpenAI | 40.5 | — | 1 of 4 categories | 21.8 | |||
| 424 | Hunyuan Large Visiontencent/hunyuan-large-vision | Tencent | 40.4 | — | 3 of 4 categories | 40.9 | 35.6 | 26.0 | |
| 425 | Llama 3.1 70B Instructmeta-llama/llama-3.1-70b-instruct | Meta | 40.4 | $0.40 / $0.40 | 2 of 4 categories | 38.7 | 23.3 | ||
| 426 | Step 1o Turbo 202506stepfun/step-1o-turbo-202506 | StepFun | 40.2 | — | 3 of 4 categories | 40.2 | 37.1 | 23.9 | |
| 427 | Gemma 3 27Bgoogle/gemma-3-27b-it | 40.1 | $0.08 / $0.45 | 3 of 4 categories | 41.2 | 35.8 | 24.0 | ||
| 428 | Qwen2.5 Coder 32B Instructqwen/qwen2.5-coder-32b-instruct | Qwen | 39.7 | — | 3 of 4 categories | 33.4 | 30.5 | 35.1 | |
| 429 | Gemini 1.5 Flash 8B 001google/gemini-1.5-flash-8b-001 | 39.7 | — | 3 of 4 categories | 36.7 | 26.0 | 36.3 | ||
| 430 | Claude 2anthropic/claude-2 | Anthropic | 39.4 | — | 2 of 4 categories | 32.8 | 25.1 | ||
| 431 | Llama 3.1 8B Instructmeta-llama/llama-3.1-8b-instruct | Meta | 39.3 | $0.05 / $0.08 | 2 of 4 categories | 36.5 | 20.9 | ||
| 432 | Gemini 1.5 Flash 001google/gemini-1.5-flash-001 | 39.2 | — | 3 of 4 categories | 38.0 | 22.8 | 35.7 | ||
| 433 | Claude 3 Opusanthropic/claude-3-opus | Anthropic | 39.2 | — | 3 of 4 categories | 34.3 | 26.1 | 36.0 | |
| 434 | Claude 3.5 Haikuanthropic/claude-3-5-haiku | Anthropic | 39.2 | — | 3 of 4 categories | 52.4 | 23.1 | 20.7 | |
| 435 | Claude 3 Sonnetanthropic/claude-3-sonnet | Anthropic | 38.9 | — | 3 of 4 categories | 38.6 | 21.5 | 34.8 | |
| 436 | Gemini 2.0 Flash 001google/gemini-2.0-flash-001 | 38.5 | — | 4 of 4 categories | 34.8 | 33.3 | 35.7 | 27.7 | |
| 437 | Claude 3 Haikuanthropic/claude-3-haiku | Anthropic | 37.7 | $0.25 / $1.25 | 3 of 4 categories | 33.6 | 20.8 | 34.6 | |
| 438 | Llama 4 Maverick 17B 128e Instructmeta-llama/llama-4-maverick-17b-128e-instruct | Meta | 37.4 | — | 4 of 4 categories | 35.6 | 34.3 | 31.1 | 23.6 |
| 439 | Mistral Small 3.1 24B Instruct 2503mistralai/mistral-small-3.1-24b-instruct-2503 | Mistral AI | 37.2 | — | 3 of 4 categories | 41.5 | 26.9 | 17.9 | |
| 440 | Llama 4 Scout 17B 16e Instructmeta-llama/llama-4-scout-17b-16e-instruct | Meta | 35.6 | — | 4 of 4 categories | 34.1 | 32.6 | 26.5 | 21.1 |
How this ranks
Every benchmark value becomes a percentile among the models that have it, so accuracy scores, Elo ratings and word error rates compare without hand-tuned scaling. Metrics where lower is better are inverted first. Raw values are never summed or averaged across benchmarks. A model's mean percentile is then shrunk toward the mean of the models that were broadly benchmarked, so a model tested twice cannot outrank a broadly tested one on two lucky results. Turning a data source off runs that same ranking code again in your browser over the sources you left on.
A model ranks here on however many of the 4 text categories it has been scored in, and the coverage column says how many that is. Each category score is itself a shrunk mean of that model's benchmark percentiles, so a composite standing on one category sits near the middle of the board rather than at the top of it.
Data sources
Turn a source off to drop every benchmark it feeds and rank the board again from what is left, in your browser. Turn them all off and the table has nothing to rank. Your choice follows you across the leaderboard pages.
- Epoch AI Benchmarking HubCC BY 4.0
Benchmark runs by Epoch AI, from the AI Benchmarking Hub.
- LMArenaCC BY 4.0
Arena ratings by LMArena, from the public leaderboard dataset.
- Open ASR Leaderboard
Word error rates from the Hugging Face Open ASR Leaderboard.
- SWE-bench
Resolve rates published by the SWE-bench maintainers.
- TTS Arena V2
Elo ratings from TTS Arena V2.
- Warden
Security review results published by Warden.