Benchmark
MMMU-Pro (with tools) Benchmark
What is MMMU-Pro (with tools)?
MMMU-Pro variant evaluated with tool access enabled. Benchmark Radar tracks 4 reported scores for MMMU-Pro (with tools), cited by 1 source documents.
- Modality
- multimodal
- Evaluates
- multimodal, reasoning, general, vision
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 4
Source provenance
MMMU-Pro (with tools) results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| GPT-5.6 Luna | OpenAI | 0.795 | 2026-07-09 | evidence |
| GPT-5.6 Sol | OpenAI | 0.846 | 2026-07-09 | evidence |
| GPT-5.6 Terra | OpenAI | 0.82 | 2026-07-09 | evidence |
| Kimi K3 | Moonshot AI | 0.834 | 2026-07-16 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.