LiveBench Global Average
LiveBench · Continually refreshes automatically checkable questions to see whether models remain strong on new problems.
What it measures and how
The official Global Average is an overall reference. Ranked scores use distinct specialist tasks.
How this evidence is used
The original Global Average is reference only; ranking evidence uses distinct specialist tasks.
Evaluation results
Fixed rules select one representative configuration per public model. Anonymous test models are omitted. Original ranks are retained, with up to 30 models per evaluation.
| Source rank | Source model name | Raw result | Representative configuration |
|---|---|---|---|
| 1 | claude-fable-5-1-max-effortAnthropic | 83.4% | Max reasoning |
| 2 | claude-opus-5-5-max-effortAnthropic | 83.2% | Max reasoning |
| 3 | claude-fable-5-max-effortAnthropic | 83.0% | Max reasoning |
| 4 | gpt-6-astra-maxOpenAI | 82.2% | Max reasoning |
| 6 | gpt-6.1-sol-maxopenai | 81.6% | Max reasoning |
| 7 | muse-spark-1.3-xhighMeta | 81.6% | xHigh reasoning |
| 8 | muse-wonder-1.0-max— | 81.2% | Max reasoning |
| 10 | deepseek-v4.1-flash-maxDeepSeek | 81.1% | Source default |
| 11 | gpt-5.6-sol-maxOpenAI | 81.1% | Max reasoning |
| 12 | gpt-5.5-xhighOpenAI | 80.2% | xHigh reasoning |
| 13 | claude-opus-5-max-effortAnthropic | 80.1% | Max reasoning |
| 14 | smaug-agenticAbacus.AI | 79.5% | Source default |
| 15 | gpt-6-sol-maxOpenAI | 79.2% | Max reasoning |
| 16 | kimi-k3Moonshot AI | 79.2% | Source default |
| 17 | gemini-3.7-flash-highGoogle | 78.8% | High reasoning |
| 18 | qwen3.8-maxAlibaba | 78.5% | Source default |
| 19 | grok-4.6xAI | 78.0% | Source default |
| 20 | gpt-5.4-xhighOpenAI | 78.0% | xHigh reasoning |
| 21 | muse-spark-1.2-xhighMeta | 78.0% | xHigh reasoning |
| 22 | gpt-5.6-terra-maxOpenAI | 77.9% | Max reasoning |
| 24 | deepseek-v4-pro-0813DeepSeek | 77.4% | Source default |
| 25 | smaug-flashAbacus.AI | 77.4% | Source default |
| 26 | grok-4.7-xhighxAI | 77.4% | xHigh reasoning |
| 27 | gemini-3.1-pro-preview-highGoogle | 77.0% | High reasoning |
| 28 | smaug-miniAbacus.AI | 76.9% | Source default |
| 29 | deepseek-v4-flash-vision-expDeepSeek | 76.8% | Source default |
| 30 | claude-opus-4-7-xhigh-effortAnthropic | 76.5% | xHigh reasoning |
| 31 | claude-opus-4-8-max-effortAnthropic | 76.2% | Max reasoning |
| 32 | qwen3.8-flash-nextAlibaba | 76.2% | Source default |
| 33 | glm-5.3Z.ai | 76.1% | Source default |
Evaluation limits & attribution
Overall averages can obscure changes in individual abilities. Cross-reference only, without double counting. Organizer Abacus.AI also develops Smaug; exclusive results need independent corroboration.
Data license: Apache 2.0
Results are published by LiveBench. Original scores and the NexGateHub consensus index use different scales and cannot be added directly.