Claw-some AI Agent Testing
| When | Model | Provider | Score | Cost | Time | Bench Version | OpenClaw | Client |
|---|---|---|---|---|---|---|---|---|
| about 23 hours ago | inception/mercury-2 | inception | 24.6% | $0.47 | 67.3m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| about 23 hours ago | inception/mercury-2 | inception | 22.6% | $0.48 | 53.9m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| about 23 hours ago | inception/mercury-2 | inception | 24.4% | $0.60 | 52.7m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| about 23 hours ago | inception/mercury-2 | inception | 28.4% | $0.62 | 49.3m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| about 23 hours ago | inception/mercury-2 | inception | 23.8% | $0.64 | 45.8m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 4 days ago | google/gemini-3.5-flash | 74.1% | $35.38 | 177.6m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | | |
| 4 days ago | google/gemini-3.5-flash | 71.0% | $25.84 | 156.1m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | | |
| 4 days ago | google/gemini-3.5-flash | 74.1% | $37.14 | 163.8m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | | |
| 4 days ago | google/gemini-3.5-flash | 75.3% | $35.48 | 163.5m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | | |
| 4 days ago | google/gemini-3.5-flash | 76.3% | $38.24 | 161.1m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | | |
| 9 days ago | openai/gpt-5.5-pro | openai | 29.9% | $371.65 | 470.3m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 9 days ago | deepseek/deepseek-v4-pro | deepseek | 60.9% | - | 383.0m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 9 days ago | nvidia/nemotron-3-super-120b-a12b | nvidia | 53.0% | - | 375.1m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 9 days ago | google/gemma-4-31b-it | 62.6% | $1.94 | 358.0m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | | |
| 9 days ago | anthropic/claude-opus-4.6 | anthropic | 83.1% | $83.79 | 289.7m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 9 days ago | z-ai/glm-5v-turbo | z-ai | 83.8% | $35.39 | 290.5m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 9 days ago | anthropic/claude-sonnet-4.6 | anthropic | 84.6% | $46.83 | 285.1m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 9 days ago | z-ai/glm-5-turbo | z-ai | 88.2% | $14.06 | 270.9m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 9 days ago | google/gemma-4-26b-a4b-it | 72.4% | $1.35 | 254.5m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | | |
| 9 days ago | mistralai/devstral-2512 | mistralai | 79.6% | $6.61 | 246.1m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 9 days ago | anthropic/claude-opus-4.7 | anthropic | 91.0% | $84.31 | 239.1m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 9 days ago | deepseek/deepseek-v4-flash | deepseek | 89.5% | $1.21 | 231.5m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 9 days ago | openai/gpt-5.4 | openai | 88.4% | $23.68 | 214.6m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 9 days ago | anthropic/claude-haiku-4.5 | anthropic | 90.4% | $19.68 | 213.2m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 9 days ago | arcee-ai/trinity-large-thinking | arcee-ai | 71.2% | $3.66 | 204.2m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 9 days ago | xiaomi/mimo-v2.5 | xiaomi | 91.4% | $6.03 | 188.3m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 9 days ago | x-ai/grok-4.3 | x-ai | 76.3% | $19.60 | 171.3m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 9 days ago | arcee-ai/trinity-large-preview | arcee-ai | 71.2% | $5.51 | 166.1m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 9 days ago | openai/gpt-5.4-mini | openai | 86.4% | $5.17 | 131.4m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 9 days ago | google/gemini-3-flash-preview | 75.0% | $6.30 | 111.1m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | | |
| 9 days ago | openai/gpt-oss-20b | openai | 36.0% | $0.49 | 98.2m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 9 days ago | amazon/nova-2-lite-v1 | amazon | 40.0% | $5.37 | 101.4m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 12 days ago | inclusionai/ling-2.6-1t | inclusionai | 82.6% | $7.00 | 239.9m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | openai/gpt-5.5-pro | openai | 14.0% | $173.44 | 469.7m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | deepseek/deepseek-v4-pro | deepseek | 59.2% | - | 385.2m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | openai/gpt-5.5-pro | openai | 11.5% | $153.44 | 481.4m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | nvidia/nemotron-3-super-120b-a12b | nvidia | 60.4% | - | 351.6m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | deepseek/deepseek-v4-flash | deepseek | 70.3% | $1.67 | 335.5m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | google/gemma-4-31b-it | 63.4% | $2.23 | 331.8m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | | |
| 15 days ago | z-ai/glm-5.1 | z-ai | 76.6% | $19.84 | 314.8m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | moonshotai/kimi-k2.5 | moonshotai | 79.3% | $10.60 | 315.1m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | minimax/minimax-m2.7 | minimax | 68.2% | $4.54 | 300.8m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | deepseek/deepseek-v4-pro | deepseek | 56.5% | - | 383.9m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | anthropic/claude-sonnet-4.6 | anthropic | 80.1% | $49.97 | 283.8m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | google/gemma-4-26b-a4b-it | 77.1% | $2.03 | 274.3m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | | |
| 15 days ago | z-ai/glm-5-turbo | z-ai | 86.2% | $14.29 | 270.8m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | qwen/qwen3.6-plus | qwen | 83.3% | $15.75 | 266.7m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | anthropic/claude-opus-4.6 | anthropic | 85.9% | $83.34 | 263.4m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | z-ai/glm-5v-turbo | z-ai | 86.6% | $32.82 | 255.5m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | nvidia/nemotron-3-super-120b-a12b | nvidia | 56.2% | - | 369.0m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | google/gemma-4-31b-it | 59.2% | $2.17 | 359.7m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | | |
| 15 days ago | z-ai/glm-5.1 | z-ai | 72.2% | $19.99 | 346.0m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | stepfun/step-3.5-flash | stepfun | 82.5% | $0.96 | 241.4m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | anthropic/claude-opus-4.7 | anthropic | 89.6% | $85.51 | 238.4m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | mistralai/devstral-2512 | mistralai | 80.2% | $6.46 | 229.2m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | deepseek/deepseek-v4-flash | deepseek | 72.0% | $1.65 | 338.0m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | xiaomi/mimo-v2.5-pro | xiaomi | 88.0% | $12.27 | 221.3m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | mistralai/mistral-large-2512 | mistralai | 70.5% | $9.95 | 219.8m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | moonshotai/kimi-k2.5 | moonshotai | 72.2% | $10.37 | 331.9m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | mistralai/mistral-small-2603 | mistralai | 71.0% | $3.84 | 220.5m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | anthropic/claude-haiku-4.5 | anthropic | 89.0% | $18.52 | 214.4m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | openai/gpt-5.5 | openai | 82.9% | $35.78 | 210.4m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | arcee-ai/trinity-large-thinking | arcee-ai | 66.3% | $3.79 | 209.1m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | xiaomi/mimo-v2.5 | xiaomi | 89.2% | $5.44 | 200.4m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | bytedance-seed/seed-2.0-lite | bytedance-seed | 86.1% | $6.63 | 192.2m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | openai/gpt-5.4 | openai | 84.8% | $23.31 | 191.6m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | deepseek/deepseek-v4-pro | deepseek | 57.3% | - | 390.7m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | minimax/minimax-m2.7 | minimax | 66.7% | $4.42 | 297.5m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | z-ai/glm-5v-turbo | z-ai | 82.7% | $35.84 | 290.2m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | google/gemma-4-26b-a4b-it | 72.3% | $1.94 | 282.0m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | | |
| 15 days ago | anthropic/claude-sonnet-4.6 | anthropic | 79.5% | $47.06 | 285.9m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | qwen/qwen3.6-plus | qwen | 84.4% | $13.48 | 278.9m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | z-ai/glm-5.1 | z-ai | 66.3% | $18.45 | 367.4m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | google/gemma-4-31b-it | 62.9% | $2.21 | 357.1m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | | |
| 15 days ago | x-ai/grok-4.3 | x-ai | 55.6% | $16.70 | 160.9m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | openai/gpt-5.4-nano | openai | 71.7% | $1.51 | 153.8m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | stepfun/step-3.5-flash | stepfun | 82.6% | $1.06 | 259.9m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | z-ai/glm-5-turbo | z-ai | 66.2% | $11.95 | 261.6m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | anthropic/claude-opus-4.6 | anthropic | 87.3% | $87.06 | 265.6m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | openai/gpt-oss-120b | openai | 43.2% | $0.58 | 157.9m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | google/gemini-3.1-pro-preview | 82.4% | $25.24 | 156.4m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | | |
| 15 days ago | arcee-ai/trinity-large-preview | arcee-ai | 66.4% | $6.12 | 153.0m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | arcee-ai/trinity-large-thinking | arcee-ai | 67.8% | $4.11 | 251.7m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | x-ai/grok-4.20 | x-ai | 80.3% | $31.14 | 142.5m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | xiaomi/mimo-v2.5-pro | xiaomi | 89.5% | $12.55 | 242.0m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | openai/gpt-5.4 | openai | 84.3% | $21.81 | 237.7m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | google/gemini-3-flash-preview | 75.8% | $7.43 | 130.6m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | | |
| 15 days ago | minimax/minimax-m2.7 | minimax | 62.3% | $4.16 | 337.5m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | mistralai/mistral-small-2603 | mistralai | 76.9% | $4.31 | 245.5m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | openai/gpt-5.4-mini | openai | 81.3% | $5.38 | 136.7m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | moonshotai/kimi-k2.5 | moonshotai | 79.4% | $10.11 | 334.9m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | anthropic/claude-opus-4.7 | anthropic | 88.5% | $90.17 | 236.5m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | mistralai/mistral-large-2512 | mistralai | 72.4% | $9.21 | 230.7m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | xiaomi/mimo-v2.5 | xiaomi | 88.2% | $6.74 | 224.2m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | openai/gpt-5.5 | openai | 82.8% | $35.11 | 222.1m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | openai/gpt-oss-20b | openai | 34.1% | $0.49 | 101.3m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | anthropic/claude-sonnet-4.6 | anthropic | 81.6% | $49.44 | 297.0m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | anthropic/claude-haiku-4.5 | anthropic | 88.2% | $18.16 | 193.2m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | amazon/nova-2-lite-v1 | amazon | 35.3% | $5.78 | 86.5m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |
| 15 days ago | mistralai/devstral-2512 | mistralai | 81.6% | $7.11 | 192.1m | 2.0.0 | OpenClaw 2026.5.4 (325df3e) | |