TestsBenchmarks · Agentic
Agents' Last Exam
Long-horizon, economically valuable computer tasks spanning 55 sub-industries.
Measured by independent testersIndependent Reported by the makerVendor-reported
| Thinking levelSetting | |||||||
|---|---|---|---|---|---|---|---|
| 1 | GPT-6 Astra | OpenAI | 59.3% | Maxreasoning effort=max | Maker's own figureVendor-reportedOpenAI ↗ | — | 22 Sep 2026 |
| 2 | GPT-6 Sol | OpenAI | 56.4% | Maxreasoning effort=max | Maker's own figureVendor-reportedOpenAI ↗ | — | 22 Sep 2026 |
| 3 | Claude Opus 5 | Anthropic | 55.9% | Higheffort=high | Independent testIndependentOpenAI (competitor result in OpenAI launch post) ↗ | — | 22 Sep 2026 |
| 4 | GPT-5.6 Sol | OpenAI | 53.6% | Extra highreasoning effort=xhigh | Maker's own figureVendor-reportedOpenAI ↗ | — | 22 Sep 2026 |
| 5 | GPT-6 Luna | OpenAI | 50.9% | Maxreasoning effort=max | Maker's own figureVendor-reportedOpenAI ↗ | — | 22 Sep 2026 |
| 6 | GPT-5.6 Terra | OpenAI | 50.4% | DefaultGPT-5.6 launch table (effort not stated; text cites max for headline results) | Maker's own figureVendor-reportedOpenAI ↗ | — | 9 Jul 2026 |
| 7 | GPT-5.6 Luna | OpenAI | 50.4% | Maxreasoning effort=max | Maker's own figureVendor-reportedOpenAI ↗ | — | 22 Sep 2026 |
| 8 | Claude Fable 5 | Anthropic | 48.7% | Extra higheffort=xhigh | Independent testIndependentOpenAI (competitor result in OpenAI launch post) ↗ | — | 22 Sep 2026 |
| 9 | GPT-5.5 | OpenAI | 46.9% | DefaultGPT-5.6 launch table (effort not stated; text cites max for headline results) | Maker's own figureVendor-reportedOpenAI ↗ | — | 9 Jul 2026 |
| 10 | Gemini 4 Argon | Google (Gemini / DeepMind) | 39.5% | Maxhighest thinking settings | Maker's own figureVendor-reportedGoogle ↗ | ALE-Claw | 30 Sep 2026 |
| 11 | DeepSeek V4.1 Flash | DeepSeek | 31.8% | Maxreasoning_effort=100 (max) | Maker's own figureVendor-reportedDeepSeek ↗ | official scaffold | 10 Sep 2026 |
| 12 | GLM-5.3 | Z.ai (Zhipu) | 28.5% | Maxreasoning_effort=max | Maker's own figureVendor-reportedZ.ai ↗ | Claude Code | 14 Aug 2026 |
| 13 | Kimi K3 | Moonshot AI (Kimi) | 28.3% | Maxreasoning_effort=max | Maker's own figureVendor-reportedMoonshot AI ↗ | Kimi Code | 16 Jul 2026 |
| 14 | DeepSeek V4 Flash Vision Exp | DeepSeek | 27.3% | Maxreasoning_effort=max | Maker's own figureVendor-reportedDeepSeek ↗ | — | 21 Aug 2026 |
| 15 | Qwen3.8 Max (0803) | Qwen (Alibaba) | 27.0% | Defaultthinking (default reasoning_effort=xhigh; eval setting not stated) | Maker's own figureVendor-reportedQwen (Alibaba) ↗ | — | 3 Aug 2026 |
| 16 | Gemini 3.7 Flash | Google (Gemini / DeepMind) | 26.3% | Defaultdefault settings (API default thinking_level=medium) | Maker's own figureVendor-reportedGoogle ↗ | ALE-Claw | 13 Aug 2026 |
| 17 | GLM-5.3-Flash | Z.ai (Zhipu) | 26.3% | Maxreasoning_effort=max (default) | Maker's own figureVendor-reportedZ.ai ↗ | Claude Code | 26 Aug 2026 |
| 18 | DeepSeek V4 Pro (0813) | DeepSeek | 25.7% | Maxreasoning_effort=max | Maker's own figureVendor-reportedDeepSeek ↗ | — | 13 Aug 2026 |
| 19 | DeepSeek V4 Flash (0731) | DeepSeek | 25.2% | Maxreasoning_effort=max | Maker's own figureVendor-reportedDeepSeek ↗ | — | 31 Jul 2026 |
| 20 | Qwen3.8 Flash | Qwen (Alibaba) | 24.3% | Defaultthinking (setting not stated) | Maker's own figureVendor-reportedQwen (Alibaba) ↗ | — | 26 Aug 2026 |
| 21 | Gemini 3.6 Flash | Google (Gemini / DeepMind) | 24.2% | Defaultdefault settings (API default thinking_level=medium) | Maker's own figureVendor-reportedGoogle ↗ | ALE-Claw | 13 Aug 2026 |
| 22 | GLM-5.2 | Z.ai (Zhipu) | 23.8% | Maxsetting not stated (GLM-5.3 blog comparison column) | Maker's own figureVendor-reportedZ.ai ↗ | — | 14 Aug 2026 |
| 23 | Qwen3.8 27B | Qwen (Alibaba) | 20.4% | Defaultthinking (default reasoning_effort=xhigh; eval setting not stated) | Maker's own figureVendor-reportedQwen (Alibaba) ↗ | — | 14 Aug 2026 |
| 24 | DeepSeek V4 Pro (Preview, 0423) | DeepSeek | 16.5% | Defaultsetting not stated for preview columns | Maker's own figureVendor-reportedDeepSeek ↗ | — | 13 Aug 2026 |
| 25 | DeepSeek V4 Flash (Preview, 0423) | DeepSeek | 15.8% | Defaultsetting not stated for preview columns | Maker's own figureVendor-reportedDeepSeek ↗ | — | 13 Aug 2026 |
| 26 | Qwen3.7 Max | Qwen (Alibaba) | 11.8% | Defaultthinking (setting not stated) | Maker's own figureVendor-reportedQwen (Alibaba) ↗ | — | 3 Aug 2026 |