| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 61 | GPT OSS 20B High gpt-oss-20b-high textinference | OpenAI | 52.3 overall | 52.3 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 62 | Seed 2.0 Lite seed-2.0-lite multimodalvisionmulti-input reasoning | ByteDance | 51.9 overall | 56.5 | 0.0 | 0.0 | 46.1 | 0.0 | N/A |
| 63 | Seed 2.0 Pro seed-2.0-pro multimodalvisionmulti-input reasoning | ByteDance | 51.0 overall | 66.8 | 23.2 | 44.8 | 56.0 | 54.9 | $0.5 in / $3 out |
| 64 | Grok-3 Mini grok-3-mini multimodalvisionmulti-input reasoning | xAI | 51.0 overall | 51.0 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 65 | MiMo-V2-Omni mimo-v2-omni multimodalvisionmulti-input reasoning | Xiaomi | 50.9 overall | 0.0 | 0.0 | 0.0 | 50.9 | 0.0 | N/A |
| 66 | Claude Sonnet 4.5 claude-sonnet-4-5-20250929 multimodalvisionmulti-input reasoning | Anthropic | 50.8 overall | 51.4 | 12.6 | 69.9 | 74.6 | 12.0 | |
| 67 | MiniMax M2.1 minimax-m2.1 codeprogrammingtool use | MiniMax | 50.7 overall | 39.1 | 68.9 | 45.7 | 47.6 | 72.9 | $0.3 in / $1.2 out |
| 68 | Nova 2 Pro nova-2-pro multimodalvisionmulti-input reasoning | Amazon | 50.4 overall | 45.3 | 0.0 | 57.2 | 49.6 | 0.0 | N/A |
| 69 | GPT-5.4 gpt-5.4 texttext-to-textlanguage | OpenAI | 50.3 overall | 70.5 | 37.2 | 48.9 | 50.3 | 18.5 | |
| 70 | Kimi K2.5 kimi-k2.5 multimodalvisionmulti-input reasoning | Moonshot AI | 49.8 overall | 63.7 | 0.0 | 41.0 | 41.8 | 0.0 | N/A |
| 71 | GPT-5 Codex gpt-5-codex-2025-09-15 codeprogrammingtool use | OpenAI | 49.8 overall | 0.0 | 0.0 | 0.0 | 49.8 | 0.0 | N/A |
| 72 | Grok-3 grok-3 multimodalvisionmulti-input reasoning | xAI | 49.6 overall | 58.4 | 50.2 | 0.0 | 0.0 | 24.1 | $3 in / $15 out |
| 73 | Gemma 4 26B-A4B gemma-4-26b-a4b-it multimodalvisionmulti-input reasoning | Google | 49.2 overall | 43.8 | 32.9 | 0.0 | 0.0 | 90.2 | |
| 74 | Grok-4 grok-4 multimodalvisionmulti-input reasoning | xAI | 49.1 overall | 49.1 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 75 | GLM-5V-Turbo glm-5v-turbo multimodalvisionmulti-input reasoning | Zhipu AI | 49.1 overall | 0.0 | 0.0 | 49.1 | 0.0 | 0.0 | N/A |
| 76 | Qwen3.5-122B-A10B qwen3.5-122b-a10b multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 48.8 overall | 60.5 | 0.0 | 44.6 | 38.3 | 0.0 | N/A |
| 77 | MAI-Thinking-1 mai-thinking-1 codeprogrammingtool use | Microsoft | 47.8 overall | 60.1 | 0.0 | 0.0 | 32.2 | 0.0 | N/A |
| 78 | GPT-5.5 Instant gpt-5.5-instant multimodalvisionmulti-input reasoning | OpenAI | 47.5 overall | 49.5 | 62.8 | 0.0 | 0.0 | 17.3 | |
| 79 | GPT-5.1 Codex gpt-5.1-codex multimodalvisionmulti-input reasoning | OpenAI | 47.2 overall | 0.0 | 0.0 | 0.0 | 47.2 | 0.0 | N/A |
| 80 | Step3-VL-10B step3-vl-10b multimodalvisionmulti-input reasoning | StepFun | 46.9 overall | 46.9 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
61
GPT OSS 20B High
OpenAI
52.3
N/A
62
Seed 2.0 Lite
ByteDance
51.9
N/A
63
Seed 2.0 Pro
ByteDance
51.0
$0.5 in / $3 out
64