Multimodal · Benchmark profile
Tool-augmented MMMU-Pro variant that allows Python assistance during multimodal reasoning.
Data verified 21 Jul 2026 · Methodology 1.6.0
Benchmark score on MMMU-Pro with Python
GPT-5.6 Sol leads at 84.6%, followed by Kimi K3 (83.4%) and GPT-5.5 (83.2%).
Visual analysis
Switch between model placement, score distribution and descriptive provider averages. Every view uses the same sourced leaderboard.
9 ranked models · higher is better
| Model | Rank | Provider | Score |
|---|---|---|---|
| GPT-5.6 Sol | #1 | OpenAI | 84.6% |
| Kimi K3 | #2 | Moonshot AI | 83.4% |
| GPT-5.5 | #3 | OpenAI | 83.2% |
| GPT-5.4 | #4 | OpenAI | 82.1% |
| GPT-5.6 Terra | #5 | OpenAI | 82% |
| Kimi K2.6 | #6 | Moonshot AI | 80.1% |
| GPT-5.6 Luna | #7 | OpenAI | 79.5% |
| GPT-5.4 mini | #8 | OpenAI | 78% |
| GPT-5.4 nano | #9 | OpenAI | 69.5% |
One best score per model · higher is better
| Rank | Model | Provider | License | Evidence use | Score |
|---|---|---|---|---|---|
| #1 | GPT-5.6 Sol gpt-5.6-sol | OpenAI | closed | Reference only | 84.6% |
| #2 | Kimi K3 kimi-k3 | Moonshot AI | closed | Reference only | 83.4% |
| #3 | GPT-5.5 gpt-5.5 | OpenAI | closed | Estimated reference | 83.2% |
| #4 | GPT-5.4 gpt-5.4 | OpenAI | closed | Reference only | 82.1% |
| #5 | GPT-5.6 Terra gpt-5.6-terra | OpenAI | closed | Estimated reference | 82% |
| #6 | Kimi K2.6 kimi-k2.6 | Moonshot AI | open | Estimated reference | 80.1% |
| #7 | GPT-5.6 Luna gpt-5.6-luna | OpenAI | closed | Estimated reference | 79.5% |
| #8 | GPT-5.4 mini gpt-5.4-mini | OpenAI | closed | Estimated reference | 78% |
| #9 | GPT-5.4 nano gpt.5.4.nano | OpenAI | closed | Reference only | 69.5% |
The top of this snapshot is led by GPT-5.6 Sol at 84.6%; third place is 1.4 points behind. The top-9 spread is 15.1 points.
About MMMU-Pro with Python
Tool-augmented MMMU-Pro variant that allows Python assistance during multimodal reasoning. Results stay tied to the exact model variant and evaluation system. Multiple systems for the same model use the best published score on this page; overall Lumina scoring uses the median of ranking-eligible rows.
Open benchmark source ↗FAQ
Tool-augmented MMMU-Pro variant that allows Python assistance during multimodal reasoning.
GPT-5.6 Sol by OpenAI currently leads with 84.6%.
9 models in the LuminaBench cohort have a qualifying score on this benchmark.
No. This benchmark is display-only and does not enter the overall Lumina composite.
Related
