| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 41 | Muse Wonder muse-wonder-1.0 multimodalvisionmulti-input reasoning | Meta | 85.2 Inference | 0.0 | 85.2 | 0.0 | 0.0 | 7.4 | $4 in / $20 out |
| 42 | Qwen3.8 Max qwen3.8-max multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 85.2 Inference | 70.5 | 85.2 | 62.9 | 69.9 | 25.8 | $1.65 in / $4.951 out |
| 43 | GPT-4.1 mini gpt-4.1-mini-2025-04-14 multimodalvisionmulti-input reasoning | OpenAI | 84.1 Inference | 17.8 | 84.1 | 8.9 | 1.9 | 57.0 | |
| 44 | GPT-5 mini gpt-5-mini-2025-08-07 multimodalvisionmulti-input reasoning | OpenAI | 79.9 Inference | 38.2 | 79.9 | 0.0 | 22.2 | 56.3 | |
| 45 | LongCat-Flash-Lite longcat-flash-lite codeprogrammingtool use | Meituan | 75.2 Inference | 21.7 | 75.2 | 30.1 | 23.6 | 83.7 | $0.1 in / $0.4 out |
| 46 | Ember-1 ember-1 codeprogrammingtool use | Fireworks AI | 74.3 Inference | 0.0 | 74.3 | 0.0 | 74.6 | 9.1 | $3 in / $15 out |
| 47 | Mercury 2 mercury-2 codeprogrammingtool use | Inception | 69.0 Inference | 41.7 | 69.0 | 0.0 | 19.2 | 73.4 | $0.25 in / $0.75 out |
| 48 | GPT-4.1 gpt-4.1-2025-04-14 multimodalvisionmulti-input reasoning | OpenAI | 68.7 Inference | 25.9 | 68.7 | 32.8 | 14.2 | 30.2 | |
| 49 | Claude Fable 5 claude-fable-5 multimodalvisionmulti-input reasoning | Anthropic | 66.7 Inference | 69.6 | 66.7 | 0.0 | 82.7 | 1.1 | |
| 50 | Claude Fable 5.1 claude-fable-5-1 multimodalvisionmulti-input reasoning | Anthropic | 66.7 Inference | 71.6 | 66.7 | 0.0 | 0.0 | 1.1 | |
| 51 | Claude Haiku 5.5 claude-haiku-5-5 multimodalvisionmulti-input reasoning | Anthropic | 66.7 Inference | 0.0 | 66.7 | 0.0 | 67.4 | 77.2 | |
| 52 | Claude Opus 4.8 claude-opus-4-8 multimodalvisionmulti-input reasoning | Anthropic | 66.7 Inference | 72.8 | 66.7 | 68.9 | 80.3 | 5.5 | |
| 53 | Claude Opus 5 claude-opus-5 multimodalvisionmulti-input reasoning | Anthropic | 66.7 Inference | 70.6 | 66.7 | 69.6 | 0.0 | 5.5 | |
| 54 | Claude Opus 5.5 claude-opus-5-5 multimodalvisionmulti-input reasoning | Anthropic | 66.7 Inference | 0.0 | 66.7 | 0.0 | 76.2 | 7.4 | |
| 55 | Gemini 2.5 Flash gemini-2.5-flash multimodalvisionmulti-input reasoning | Google | 66.7 Inference | 36.9 | 66.7 | 0.0 | 19.6 | 42.9 | |
| 56 | Gemini 3.1 Flash-Lite gemini-3.1-flash-lite-preview multimodalvisionmulti-input reasoning | Google | 66.7 Inference | 50.7 | 66.7 | 0.0 | 0.0 | 51.1 | |
| 57 | Gemini 3 Flash gemini-3-flash-preview multimodalvisionmulti-input reasoning | Google | 66.7 Inference | 67.5 | 66.7 | 28.2 | 61.8 | 38.2 | |
| 58 | Grok 4.3 grok-4.3 textinference | xAI | 66.7 Inference | 0.0 | 66.7 | 0.0 | 0.0 | 36.3 | $1.25 in / $2.5 out |
| 59 | MiniMax M3 minimax-m3 multimodalvisionmulti-input reasoning | MiniMax | 66.7 Inference | 50.3 | 66.7 | 34.4 | 65.6 | 59.3 | $0.28 in / $1.1 out |
| 60 | MiniMax M3.1 Flash minimax-m3.1-flash multimodalvisionmulti-input reasoning | MiniMax | 66.7 Inference | 47.5 | 66.7 | 0.0 | 0.0 | 70.9 |
41
Muse Wonder
Meta
85.2
$4 in / $20 out
42
Qwen3.8 Max
Alibaba Cloud / Qwen Team
85.2
$1.65 in / $4.951 out
43
GPT-4.1 mini
OpenAI
84.1
$0.4 in / $1.6 out
44