| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 1 | Claude Mythos Preview claude-mythos-preview multimodalvisionmulti-input reasoning | Anthropic | 79.5 Benchmarks | 79.5 | 0.0 | 64.8 | 83.0 | 0.0 | N/A |
| 2 | GPT-5.6 Sol gpt-5.6-sol multimodalvisionmulti-input reasoning | OpenAI | 77.6 Benchmarks | 77.6 | 95.2 | 63.1 | 72.7 | 5.8 | |
| 3 | Kimi K3 kimi-k3 multimodalvisionmulti-input reasoning | Moonshot AI | 75.3 Benchmarks | 75.3 | 81.9 | 78.2 | 0.0 | 13.1 | |
| 4 | GPT-6 Astra gpt-6-astra multimodalvisionmulti-input reasoning | OpenAI | 74.8 Benchmarks | 74.8 | 95.2 | 74.6 | 0.0 | 1.9 | $10 in / $50 out |
| 5 | Claude Opus 4.7 claude-opus-4-7 multimodalvisionmulti-input reasoning | Anthropic | 74.3 Benchmarks | 74.3 | 26.7 | 52.9 | 77.5 | 9.5 | |
| 6 | GPT-5.5 gpt-5.5 multimodalvisionmulti-input reasoning | OpenAI | 74.2 Benchmarks | 74.2 | 95.2 | 54.9 | 49.2 | 5.8 | $5 in / $30 out |
| 7 | Claude Opus 4.8 claude-opus-4-8 multimodalvisionmulti-input reasoning | Anthropic | 72.5 Benchmarks | 72.5 | 26.7 | 68.7 | 81.8 | 9.5 | |
| 8 | GPT-5.6 Terra gpt-5.6-terra multimodalvisionmulti-input reasoning | OpenAI | 72.5 Benchmarks | 72.5 | 95.2 | 54.6 | 69.3 | 21.4 | |
| 9 | Claude Opus 4.6 claude-opus-4-6 multimodalvisionmulti-input reasoning | Anthropic | 72.2 Benchmarks | 72.2 | 26.7 | 48.8 | 71.9 | 9.5 | |
| 10 | Claude Fable 5.1 claude-fable-5-1 multimodalvisionmulti-input reasoning | Anthropic | 71.6 Benchmarks | 71.6 | 58.6 | 0.0 | 0.0 | 1.9 | |
| 11 | Claude Opus 5 claude-opus-5 multimodalvisionmulti-input reasoning | Anthropic | 70.5 Benchmarks | 70.5 | 58.6 | 69.4 | 0.0 | 9.2 | |
| 12 | Gemini 3.1 Pro gemini-3.1-pro-preview multimodalvisionmulti-input reasoning | Google | 70.5 Benchmarks | 70.5 | 57.5 | 46.2 | 62.9 | 21.9 | |
| 13 | Muse Spark 1.3 muse-spark-1.3 multimodalvisionmulti-input reasoning | Meta | 70.4 Benchmarks | 70.4 | 81.9 | 0.0 | 0.0 | 95.1 | $0.1 in / $0.2 out |
| 14 | Qwen3.8 Max qwen3.8-max multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 70.3 Benchmarks | 70.3 | 81.9 | 62.7 | 72.0 | 35.0 | $1.65 in / $4.951 out |
| 15 | GPT-5.2 gpt-5.2-2025-12-11 multimodalvisionmulti-input reasoning | OpenAI | 69.8 Benchmarks | 69.8 | 58.9 | 34.3 | 66.3 | 28.7 | |
| 16 | Claude Fable 5 claude-fable-5 multimodalvisionmulti-input reasoning | Anthropic | 69.5 Benchmarks | 69.5 | 58.6 | 0.0 | 84.2 | 1.9 | |
| 17 | GPT-5.4 gpt-5.4 texttext-to-textlanguage | OpenAI | 69.3 Benchmarks | 69.3 | 35.4 | 43.6 | 49.4 | 17.6 | |
| 18 | Grok 4.5 grok-4.5 multimodalvisionmulti-input reasoning | xAI | 69.1 Benchmarks | 69.1 | 37.9 | 0.0 | 69.2 | 33.5 | $2 in / $6 out |
| 19 | Gemini 3 Pro gemini-3-pro-preview multimodalvisionmulti-input reasoning | Google | 68.8 Benchmarks | 68.8 | 0.0 | 51.0 | 52.9 | 0.0 | |
| 20 | GLM-5.3 glm-5.3 textinference | Zhipu AI | 68.8 Benchmarks | 68.8 | 81.9 | 59.9 | 0.0 | 37.4 | $1.4 in / $4.4 out |
1
Claude Mythos Preview
Anthropic
79.5
N/A
2
GPT-5.6 Sol
OpenAI
77.6
$5 in / $30 out
3
Kimi K3
Moonshot AI
75.3
$3 in / $15 out
Page 1 of 19 · 373 models