Benchmark
MCPMark Verified Pass@1
Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages. Higher is better.
- Models measured
- 8
- Scores recorded
- 8
- Sources
- 1
- IQ weight
- 0.58
Score distribution
- 83.9%
- Mean
- 86.6%
- Median
- 9%
- Std dev
- 72.8%
- 10th percentile
- 92.9%
- 90th percentile
- 71.7%
- Min
This benchmark has a weight of 0.58 for chat models, measured over 8 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | |
|---|---|---|
| 1 | Kimi K3config: kimi-k3-max, task-set: standard, task-version: verified, scope: overall· MCPMark Verified leaderboard docs | 96.1% |
| 2 | GPT 5.5config: gpt-5-5-xhigh, task-set: standard, task-version: verified, scope: overall· MCPMark Verified leaderboard docs | 92.9% |
| 3 | GPT-5.6 Solconfig: gpt-5-6-sol-max, task-set: standard, task-version: verified, scope: overall· MCPMark Verified leaderboard docs | 92.9% |
| 4 | Claude Fable 5config: claude-fable-5-max, task-set: standard, task-version: verified, scope: overall· MCPMark Verified leaderboard docs | 86.6% |
| 5 | Kimi K2.7 Codeconfig: kimi-k2-7-code, task-set: standard, task-version: verified, scope: overall· MCPMark Verified leaderboard docs | 81.9% |
| 6 | Claude Opus 4.8config: claude-opus-4-8-max, task-set: standard, task-version: verified, scope: overall· MCPMark Verified leaderboard docs | 76.4% |
| 7 | Kimi K2.6config: kimi-k2-6, task-set: standard, task-version: verified, scope: overall· MCPMark Verified leaderboard docs | 72.8% |
| 8 | DeepSeek V4 Proconfig: deepseek-v4-pro-max, task-set: standard, task-version: verified, scope: overall· MCPMark Verified leaderboard docs | 71.7% |
Tokens the model generated per task, as measured by the source. Comparable within this benchmark only.
Data credits: MCPMark (eval-sys), mcpmark.ai Verified leaderboard. Single-run Pass@1 fractions shown as percentages.