OpenVLM MMBench V1.1 CN - Function Reasoning: leaderboard
OpenCompass OpenVLM MMBench V1.1 Chinese split accuracy for function reasoning.
Metric: Accuracy (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 284 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 96.7 | #98 |
| 2 | GPT-5 Mini (2025-08-07) | 96.7 | #172 |
| 3 | InternVL3-78B | 95.6 | #352 |
| 4 | Claude 3.7 Sonnet | 95.6 | #249 |
| 5 | InternVL2.5-78B | 95.6 | #431 |
| 6 | Grok 2 (1212) | 95.6 | #496 |
| 7 | InternVL3-38B | 94.4 | #405 |
| 8 | GPT-4.1 (2025-04-14) | 94.4 | #250 |
| 9 | InternVL3-14B | 94.4 | #505 |
| 10 | Claude 3.5 Sonnet | 94.4 | #350 |
| 11 | GPT-4o ChatGPT | 94.4 | |
| 12 | Claude 3.5 Sonnet (20241022) | 93.3 | #291 |
| 13 | Gemini 1.5 Flash (002) | 93.3 | #583 |
| 14 | Pixtral-12B | 92.2 | #808 |
| 15 | Qwen 2.5 VL 7B | 92.2 | #643 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=openvlm-mmbench-v1-1-cn-function-reasoning · How It Works · Data refreshed daily, snapshot 2026-10-20.