Benchmarks · agentic
Mercor APEX
Score: best pass@1 (loop_truncated_tools_agent). Collected by Jake Boggs' benchmark dashboard.
55 models · 55 results · data as of 2026-10-29 · mercor.com ↗
Leaderboard
Gemini 4 Argon max
All results
55 rows| # | Model | Effort | Mercor APEX |
|---|---|---|---|
| 1 | Gemini 4 Argon | max | 82.4% |
| 2 | Sonnet 5.5 | max | 75.5% |
| 3 | Opus 5.5 | max | 73.5% |
| 4 | Fable 5.1 | max | 68.6% |
| 5 | Gemini 3.7 Flash | max | 67.8% |
| 6 | Opus 5 | max | 65.8% |
| 7 | Grok 4.6 | max | 65.3% |
| 8 | GPT-6 Astra | max | 64.7% |
| 9 | Gemini 3.8 Flash | max | 64.3% |
| 10 | Fable 5 | max | 63.6% |
| 11 | Qwen 3.8 Max | max | 63.3% |
| 12 | GPT-6.1 Sol | max | 60.0% |
| 13 | Muse Spark 1.3 | max | 58.6% |
| 14 | GPT-5.6 Terra | max | 58.2% |
| 15 | MiMo V2.6 Flash | high | 57.4% |
| 16 | GLM 5.3 | max | 56.6% |
| 17 | Grok 4.5 | max | 56.2% |
| 18 | Haiku 5.5 | max | 56.1% |
| 19 | DeepSeek V4 Flash | max | 55.3% |
| 20 | GPT-5.5 | xhigh | 55.1% |
| 21 | Grok 4.7 | max | 54.6% |
| 22 | Sonnet 5 | max | 54.5% |
| 23 | MiMo V2.6 Pro | high | 54.4% |
| 24 | GPT-6 Sol | max | 54.3% |
| 25 | MiniMax M3.1 | max | 53.9% |
| 26 | GLM 5.3 Flash | max | 52.8% |
| 27 | GPT-5.4 | xhigh | 52.4% |
| 28 | Mistral Large 4 | high | 51.6% |
| 29 | GPT-5.6 Sol | max | 51.5% |
| 30 | Mercury 3 | high | 50.2% |