Text, image, audio, and video combined
41
Models
24
Benchmarks
11
Providers
15
Open Weight
38
Deployable Now
16 self-host
41
Structured benchmark-backed rows
0
Signal-backed rows without full normalized tables
0
Benchmark-expected rows still catching up
| # | Model | Economic Footprint | Quality | Params | GAIA | WebArena | LiveCodeBench | BigLaw Bench | $/M In | Speed | Open |
|---|---|---|---|---|---|---|---|---|---|---|---|
85 | Claude Opus 4.8 Anthropic Subscription |
| 63.4 |
| 50.0 |
| Undisclosed |
| 58.1 |
| 84.0 |
| 62.4 |
| 10.0 |
$5.00/M Cheapest verified |
| — |
16 | GPT-4o OpenAI SubscriptionStructured | 60.6 | 41.7 | Undisclosed | 35.5 | 13.1 | 38.3 | — | $2.50/M Cheapest verified | 109 tok/s |
35 | Claude Sonnet 4.6 Anthropic SubscriptionStructured | 59.0 | 60.4 | Undisclosed | 54.5 | — | 59.4 | — | $3.00/M Cheapest verified | — |
10 | Claude 4 Sonnet Anthropic SubscriptionStructured | 53.9 | 43.5 | Undisclosed | 0.7 | 36.2 | — | — | $3.00/M Cheapest verified | 95 tok/s |
90 | Claude 3 Opus Anthropic SubscriptionStructured | 51.1 | 33.5 | Undisclosed | — | — | — | — | $15.00/M Cheapest verified | — |
1 | Kimi K2.6 Moonshot AI Open WeightsStructured | 49.9 | 80.3 | Unknown | — | — | 89.6 | — | $0.9500/M Cheapest verified | — |
32 | Claude 3.5 Haiku Anthropic SubscriptionStructured | 48.9 | 37.1 | Undisclosed | — | — | 22.5 | — | $0.8000/M Cheapest verified | — |
78 | Gemini 3 Pro | 46.8 | 57.2 | Undisclosed | 7.3 | — | — | — | $1.25/M Cheapest verified | — |
45 | Nova Pro 1.0 Amazon Structured | 46.8 | 37.7 | Undisclosed | — | — | — | — | $0.8000/M Cheapest verified | — |
33 | qwen3-7-plus Qwen Open WeightsStructured | 46.4 | 63.5 | Unknown | 44.2 | — | — | — | $0.3200/M Cheapest verified | — |
26 | Qwen2.5 VL 72B Instruct Qwen Open WeightsStructured | 46.4 | 34.9 | 72B | 4.7 | — | — | — | $0.8000/M Cheapest verified | — |
2 | Gemma 4 31B IT | 46.3 | 68.9 | 31B | — | — | 80.0 | — | $0.1200/M Cheapest verified | — |
64 | Claude 3 Haiku Anthropic SubscriptionStructured | 45.0 | 28.6 | Undisclosed | — | — | 22.5 | — | $0.2500/M Cheapest verified | — |
13 | Llama 4 Scout Meta Open WeightsStructured | 43.8 | 38.4 | Unknown | — | — | — | — | Free Cheapest verified | — |
12 | Llama 4 Maverick Meta Open WeightsStructured | 43.8 | 36.5 | Unknown | — | 22.7 | — | — | Free Cheapest verified | — |
57 | Nova Premier 1.0 Amazon Structured | 43.2 | 21.0 | Undisclosed | — | — | — | — | $2.50/M Cheapest verified | — |
23 | Mistral Medium 3 Mistral AI Open WeightsStructured | 43.1 | 39.1 | Unknown | — | — | — | — | $0.4000/M Cheapest verified | — |
82 | Gemini 1.5 Pro | 42.0 | 34.0 | Undisclosed | — | — | — | — | $1.25/M Cheapest verified | — |
53 | Kimi K2.5 Moonshot AI SubscriptionStructured | 41.3 | 52.8 | Undisclosed | — | — | — | — | $0.5700/M Cheapest verified | — |
67 | Gemini 3.1 Pro | 41.0 | 61.9 | Undisclosed | 47.2 | 40.1 | — | — | $1.25/M Cheapest verified | — |
72 | Qwen3.5-27B Qwen Self-HostStructured | 40.7 | 49.6 | 27B | 32.6 | — | — | — | $0.2600/M Cheapest verified | — |
47 | Mistral Small 3.1 24B Mistral AI Open WeightsStructured | 40.7 | 33.5 | 24B | 20.6 | — | — | — | $0.2000/M Cheapest verified | — |
34 | Grok 4.20 xAI SubscriptionStructured | 40.5 | 39.4 | Undisclosed | — | — | — | — | $1.25/M Cheapest verified | — |
61 | Qwen3 VL 8B Instruct Qwen Self-HostStructured | 39.3 | 36.5 | 8B | 44.2 | — | — | — | $0.1170/M Cheapest verified | — |
25 | Kimi K3 Moonshot AI Open WeightsStructured | 38.8 | 47.9 | Unknown | — | — | — | — | $3.00/M Cheapest verified | — |
51 | Grok 4.5 xAI SubscriptionStructured | 38.4 | 42.1 | Undisclosed | — | — | — | — | $2.00/M Cheapest verified | — |
40 | Qwen3.5 Plus 2026-04-20 Qwen Self-HostStructured | 38.2 | 40.6 | Undisclosed | 32.6 | — | — | — | $0.3000/M Cheapest verified | — |
62 | GLM-4.6V Z.ai SubscriptionStructured | 38.1 | 46.9 | Undisclosed | — | — | — | — | $0.3000/M Cheapest verified | — |
65 | Gemini 2 | 38.0 | 52.7 | Undisclosed | 30.2 | — | 75.1 | — | $1.25/M Cheapest verified | — |
66 | GLM-4.5V Z.ai SubscriptionStructured | 37.6 | 45.4 | Undisclosed | — | — | — | — | $0.6000/M Cheapest verified | — |
9 | Qwen3.6 Plus Qwen Self-HostStructured | 35.9 | 29.1 | Unknown | 44.2 | — | — | — | $0.3250/M Cheapest verified | — |
95 | Claude 3.5 Sonnet v2 Anthropic SubscriptionStructured | 35.9 | 16.2 | Undisclosed | 65.1 | — | — | — | $3.00/M Cheapest verified | — |
39 | Gemini 3 | 33.2 | 41.3 | Undisclosed | 47.2 | 40.1 | — | — | $1.25/M Cheapest verified | — |
83 | Pixtral Large 2411 Mistral AI Open WeightsStructured | 33.0 | 33.2 | Unknown | — | — | — | — | $2.00/M Cheapest verified | — |
88 | Pixtral 12B Mistral AI Open WeightsStructured | 31.6 | 32.5 | 12B | — | — | — | — | $0.1000/M Cheapest verified | — |
55 | Grok 4.1 Fast xAI SubscriptionStructured | 31.3 | 42.0 | Undisclosed | — | — | — | — | $0.2000/M Cheapest verified | — |
87 | Claude 4.5 Sonnet Anthropic SubscriptionStructured | 31.1 | 19.5 | Undisclosed | 0.7 | — | — | — | $3.00/M Cheapest verified | — |
97 | Qwen2.5-VL 7B Instruct Qwen Open WeightsStructured | 28.0 | 17.3 | 7B | 4.7 | — | — | — | $0.2000/M Cheapest verified | — |
96 | GLM-OCR Z.ai Free TrialStructured | 26.9 | 58.0 | Undisclosed | — | — | — | — | — | — |
98 | UI-TARS 7B Bytedance Structured | 23.7 | 12.9 | 7B | — | — | — | — | $0.1000/M Cheapest verified | — |
94 | Claude 4.5 Haiku Anthropic SubscriptionStructured | 22.6 | 18.5 | Undisclosed | 0.7 | — | — | — | — | — |