CAP
Vision & Multimodal
League table — best at vision & multimodal · 8
mean percentile across this capability's benchmarks| # | Model | League | Coverage | $/1M | tok/s |
|---|---|---|---|---|---|
| 1 | Gemini 2.5 Pro | 100.0 | 1/1 | $3.44 | 140 |
| 2 | GPT-4.1 | 85.7 | 1/1 | $3.5 | 128 |
| 3 | Claude 3.7 Sonnet | 71.4 | 1/1 | — | — |
| 4 | Gemini 2.0 Flash | 57.1 | 1/1 | — | — |
| 5 | GPT-4o | 42.9 | 1/1 | $4.38 | 115 |
| 6 | Claude 3.5 Sonnet | 28.6 | 1/1 | $6 | — |
| 7 | Gemini 1.5 Pro | 14.3 | 1/1 | — | — |
| 8 | Claude 3 Opus | 0.0 | 1/1 | $30 | — |
League = a model's mean percentile across the 1 benchmarkin this capability (best score per benchmark; partial coverage shown). Price & speed via Artificial Analysis.
Benchmarks in this capability (1)
MMMU8 scores