Benchmark
ClawEval-MM
What is ClawEval-MM?
ClawEval-MM is the multimodal variant of ClawEval, evaluating agentic problem solving with visual inputs. Benchmark Radar tracks 4 reported scores for…
- Modality
- multimodal
- Evaluates
- multimodal, agents, vision
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 4
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/claw-eval-mm?top_n=500
ClawEval-MM results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Qwen3.7-Plus | Qwen | 0.557 | 2026-05-31 | evidence |
| Qwen3.8-27B | Qwen | 0.569 | 2026-08-14 | evidence |
| Seed 2.1 Pro | ByteDance | 0.51 | 2026-06-24 | evidence |
| Seed 2.1 Turbo | ByteDance | 0.46 | 2026-06-24 | 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.