Text, image, audio, and video combined
10
Models
21
Benchmarks
6
Providers
6
Open Weight
10
Deployable Now
6 self-host
10
Structured benchmark-backed rows
0
Signal-backed rows without full normalized tables
0
Benchmark-expected rows still catching up
| # | Model | Adoption | Quality | Params | GPQA | MMLU-PRO | LiveCodeBench | MMLU | $/M In | Speed | Open |
|---|---|---|---|---|---|---|---|---|---|---|---|
8 | Gemma 4 26B A4B IT |
| 78.6 |
| 72.9 |
| 26B |
| 82.3 |
| 82.6 |
| 77.1 |
| 86.3 |
$0.0700/M Cheapest verified |
| — |
5 | Claude Sonnet 4.6 Anthropic SubscriptionStructured | 72.3 | 53.6 | Undisclosed | — | — | 59.4 | — | $3.00/M Cheapest verified | — |
35 | Claude 3.5 Sonnet Anthropic SubscriptionStructuredArchived | 70.9 | 49.0 | Undisclosed | — | — | 48.7 | — | $3.00/M Cheapest verified | — |
31 | Kimi K2.6 Moonshot AI Open WeightsStructured | 68.7 | 78.8 | Unknown | 91.1 | — | 89.6 | — | $0.5605/M Cheapest verified | — |
55 | GPT-4o OpenAI SubscriptionStructured | 68.0 | 48.7 | Undisclosed | 53.6 | — | 38.3 | 88.7 | $2.50/M Cheapest verified | 109 tok/s |
33 | Qwen3.7 Plus Qwen Open WeightsStructured | 67.0 | 62.8 | Unknown | 90.0 | — | — | — | $0.3200/M Cheapest verified | — |
7 | Claude 4 Sonnet Anthropic SubscriptionStructured | 59.8 | 43.1 | Undisclosed | 65.0 | — | — | 90.4 | $3.00/M Cheapest verified | 95 tok/s |
13 | Mistral Large 3 Mistral AI Open WeightsStructured | 54.6 | 40.7 | 675B | 68.0 | — | — | 80.7 | $0.5000/M Cheapest verified | — |
9 | Qwen3.6 Plus Qwen Self-HostStructured | 53.6 | 28.5 | Unknown | 88.2 | — | — | — | $0.3250/M Cheapest verified | — |
6 | Mistral Medium 3.5 Mistral AI Open WeightsStructured | 52.6 | 46.2 | 128B | 74.8 | — | — | — | $1.50/M Cheapest verified | — |