Noometry

Agentic & Tool Use benchmark

GBAEval leaderboard

As of October 2026, Claude Opus 5 has the highest published GBAEval score on Noometry at 79.6%, out of 23 models with results.

Last verified

About GBAEval

A description with primary sources is being prepared for this benchmark.

Category
Agentic & Tool Use
Introduced
2026
Unit
Percent (random guessing ≈ 0%)
Official site
epoch.ai

Top 15 models

  1. Claude Opus 5 79.6%
  2. Claude Fable 5 74.5%
  3. Claude Opus 4.8 70.9%
  4. Grok 4.5 65.4%
  5. Claude Sonnet 5 65.3%
  6. GPT-5.5 53.2%
  7. GPT-5.6 Sol 52.6%
  8. Claude Sonnet 4.6 48.8%
  9. Kimi K3 48.3%
  10. GPT-5.4 45.1%
  11. Claude Opus 4.6 44.1%
  12. Claude Opus 4.7 43.8%
  13. Muse Spark 1.1 7.9%
  14. Gemini 3.5 Flash 6.7%
  15. Grok Build 0.1 2.4%

Sponsored placements are available on pages like this one. Advertise on Noometry

All results

#ModelProviderScoreSettingSourceDate
1Claude Opus 5 Anthropic79.6%Epoch AI
2Claude Fable 5 Anthropic74.5%Epoch AI
3Claude Opus 4.8 Anthropic70.9%Epoch AI
4Grok 4.5 xAI65.4%Epoch AI
5Claude Sonnet 5 Anthropic65.3%Epoch AI
6GPT-5.5 OpenAI53.2%Epoch AI
7GPT-5.6 Sol OpenAI52.6%Epoch AI
8Claude Sonnet 4.6 Anthropic48.8%Epoch AI
9Kimi K3 Moonshot AI48.3%Epoch AI
10GPT-5.4 OpenAI45.1%Epoch AI
11Claude Opus 4.6 Anthropic44.1%Epoch AI
12Claude Opus 4.7 Anthropic43.8%Epoch AI
13Muse Spark 1.1 Meta7.9%Epoch AI
14Gemini 3.5 Flash Google6.7%Epoch AI
15Grok Build 0.1 xAI2.4%Epoch AI
16MiniMax-M3 MiniMax0.9%Epoch AI
17Kimi K2.6 Moonshot AI0.9%Epoch AI
18Kimi K2.7 Code Moonshot AI0.9%Epoch AI
19Gemini 3.1 Pro Preview Google0.8%Epoch AI
20Qwen3.7 Max Alibaba (Qwen)0.4%Epoch AI
21GLM-5.2 Z.ai (Zhipu)0%Epoch AI
22GLM-5.1 Z.ai (Zhipu)0%Epoch AI
23MiniMax-M2.7 MiniMax0%Epoch AI

Compare the leaders

Other agentic & tool use benchmarks

Frequently asked questions

Which model has the highest GBAEval score?

As of October 2026, Claude Opus 5 has the highest published GBAEval score on Noometry at 79.6%, out of 23 models with results.

What is the best open-weight model on GBAEval?

Kimi K3 has the highest GBAEval accuracy among open-weight models at 48.3%, ranking 9 of 23 overall.