| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 41 | GPT-5.2 gpt-5.2-2025-12-11 multimodalvisionmulti-input reasoning | OpenAI | 56.5 overall | 70.9 | 62.8 | 37.0 | 66.3 | 31.5 | $1.75 in / $14 out |
| 42 | Gemini 3 Flash gemini-3-flash-preview multimodalvisionmulti-input reasoning | Google | 56.3 overall | 68.5 | 62.8 | 33.2 | 61.9 | 54.9 | |
| 43 | GPT-5.2 Pro gpt-5.2-pro-2025-12-11 multimodalvisionmulti-input reasoning | OpenAI | 56.0 overall | 64.4 | 0.0 | 46.1 | 0.0 | 0.0 | |
| 44 | Step-3.5-Flash step-3.5-flash codeprogrammingtool use | StepFun | 56.0 overall | 62.8 | 59.8 | 36.5 | 48.6 | 93.9 | $0.1 in / $0.4 out |
| 45 | GPT-5.1 gpt-5.1-2025-11-13 multimodalvisionmulti-input reasoning | OpenAI | 56.0 overall | 62.4 | 62.8 | 0.0 | 51.4 | 37.3 | |
| 46 | GPT-5.1 Instant gpt-5.1-instant-2025-11-12 multimodalvisionmulti-input reasoning | OpenAI | 56.0 overall | 62.4 | 62.8 | 0.0 | 51.4 | 37.3 | |
| 47 | Claude Sonnet 5 claude-sonnet-5 multimodalvisionmulti-input reasoning | Anthropic | 55.8 overall | 67.5 | 28.3 | 60.7 | 75.4 | 12.0 | |
| 48 | Hy3 hy3 codeprogrammingtool use | Tencent | 55.6 overall | 65.9 | 0.0 | 40.4 | 59.2 | 0.0 | N/A |
| 49 | MiMo-V2.5 mimo-v2.5 multimodalvisionmulti-input reasoning | Xiaomi | 55.5 overall | 47.7 | 84.8 | 0.0 | 27.2 | 92.7 | $0.168 in / $0.336 out |
| 50 | Gemma 4 31B gemma-4-31b-it multimodalvisionmulti-input reasoning | Google | 55.4 overall | 55.4 | 32.9 | 0.0 | 0.0 | 91.5 | $0.13 in / $0.38 out |
| 51 | MiniMax M2.5 minimax-m2.5 codeprogrammingtool use | MiniMax | 55.4 overall | 0.0 | 68.9 | 43.6 | 50.4 | 72.9 | $0.3 in / $1.2 out |
| 52 | MiniMax M3 minimax-m3 multimodalvisionmulti-input reasoning | MiniMax | 55.3 overall | 49.6 | 62.8 | 37.5 | 68.3 | 73.2 | $0.3 in / $1.2 out |
| 53 | GPT-5 Medium gpt-5-medium-2025-08-07 multimodalvisionmulti-input reasoning | OpenAI | 54.6 overall | 54.6 | 0.0 | 0.0 | 0.0 | 0.0 | |
| 54 | Gemini 3.5 Flash gemini-3.5-flash multimodalvisionmulti-input reasoning | Google | 54.5 overall | 60.2 | 84.8 | 67.3 | 21.8 | 31.7 | |
| 55 | Kimi K2.6 kimi-k2.6 texttext-to-textlanguage | Moonshot AI | 54.3 overall | 63.5 | 32.9 | 47.2 | 69.4 | 46.3 | |
| 56 | Qwen3.6 Plus qwen3.6-plus multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 54.0 overall | 66.9 | 62.8 | 33.6 | 52.8 | 54.9 | $0.5 in / $3 out |
| 57 | Claude Opus 4.6 claude-opus-4-6 multimodalvisionmulti-input reasoning | Anthropic | 53.9 overall | 74.6 | 28.3 | 49.8 | 71.5 | 8.0 | |
| 58 | Claude Opus 4.5 claude-opus-4-5-20251101 multimodalvisionmulti-input reasoning | Anthropic | 53.5 overall | 54.5 | 0.0 | 35.2 | 72.2 | 0.0 | |
| 59 | ChatGPT-4o Latest chatgpt-4o-latest multimodalvisionmulti-input reasoning | OpenAI | 53.0 overall | 53.0 | 0.0 | 0.0 | 0.0 | 0.0 | |
| 60 | GPT-5.1 Medium gpt-5.1-medium-2025-11-12 multimodalvisionmulti-input reasoning | OpenAI | 52.5 overall | 64.1 | 44.9 | 0.0 | 0.0 | 32.0 |
41
GPT-5.2
OpenAI
56.5
$1.75 in / $14 out
42Google
Gemini 3 Flash
56.3
$0.5 in / $3 out
43
GPT-5.2 Pro
OpenAI
56.0
N/A
44