| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 61 | DeepSeek-V3.2-Speciale deepseek-v3.2-speciale codeprogrammingtool use | DeepSeek | 42.0 Programming | 50.7 | 0.0 | 5.0 | 42.0 | 0.0 | N/A |
| 62 | Kimi K2.5 kimi-k2.5 multimodalvisionmulti-input reasoning | Moonshot AI | 41.8 Programming | 63.7 | 0.0 | 41.0 | 41.8 | 0.0 | N/A |
| 63 | DeepSeek-V4-Flash-Max deepseek-v4-flash-max codeprogrammingtool use | DeepSeek | 41.4 Programming | 56.2 | 84.8 | 35.3 | 41.4 | 98.8 | |
| 64 | Nemotron 3 Ultra (550B A55B) nemotron-3-ultra-550b-a55b codeprogrammingtool use | NVIDIA | 40.6 Programming | 54.7 | 0.0 | 11.5 | 40.6 | 0.0 | N/A |
| 65 | MiniMax M2 minimax-m2 codeprogrammingtool use | MiniMax | 40.0 Programming | 29.8 | 62.8 | 40.2 | 40.0 | 73.2 | $0.3 in / $1.2 out |
| 66 | Qwen3.6-27B qwen3.6-27b multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 39.4 Programming | 54.7 | 32.9 | 0.0 | 39.4 | 49.4 | $0.6 in / $3.6 out |
| 67 | Qwen3.5-27B qwen3.5-27b multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 39.1 Programming | 57.8 | 32.9 | 41.3 | 39.1 | 61.0 | $0.3 in / $2.4 out |
| 68 | Qwen3.5-122B-A10B qwen3.5-122b-a10b multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 38.3 Programming | 60.5 | 0.0 | 44.6 | 38.3 | 0.0 | N/A |
| 69 | DeepSeek-V3.2-Exp deepseek-v3.2-exp codeprogrammingtool use | DeepSeek | 38.0 Programming | 50.2 | 0.0 | 27.2 | 38.0 | 0.0 | N/A |
| 70 | Claude 3.7 Sonnet claude-3-7-sonnet-20250219 multimodalvisionmulti-input reasoning | Anthropic | 37.7 Programming | 42.3 | 0.0 | 49.1 | 37.7 | 0.0 | |
| 71 | LongCat-Flash-Chat longcat-flash-chat codeprogrammingtool use | Meituan | 36.6 Programming | 26.0 | 0.0 | 48.1 | 36.6 | 0.0 | N/A |
| 72 | Muse Spark muse-spark multimodalvisionmulti-input reasoning | Meta | 36.2 Programming | 67.1 | 0.0 | 64.4 | 36.2 | 0.0 | N/A |
| 73 | GLM-4.5 glm-4.5 codeprogrammingtool use | Zhipu AI | 36.1 Programming | 31.5 | 0.0 | 36.0 | 36.1 | 0.0 | N/A |
| 74 | Grok Code Fast 1 grok-code-fast-1 codeprogrammingtool use | xAI | 36.1 Programming | 0.0 | 27.2 | 0.0 | 36.1 | 60.5 | $0.2 in / $1.5 out |
| 75 | MiMo-V2-Flash mimo-v2-flash codeprogrammingtool use | Xiaomi | 35.8 Programming | 50.6 | 0.0 | 23.5 | 35.8 | 0.0 | N/A |
| 76 | GPT-5.3 Codex gpt-5.3-codex texttext-to-textcoding | OpenAI | 34.5 Programming | 0.0 | 31.1 | 0.0 | 34.5 | 22.0 | |
| 77 | LongCat-Flash-Thinking-2601 longcat-flash-thinking-2601 codeprogrammingtool use | Meituan | 33.5 Programming | 52.9 | 0.0 | 25.6 | 33.5 | 0.0 | |
| 78 | MAI-Thinking-1 mai-thinking-1 codeprogrammingtool use | Microsoft | 32.2 Programming | 60.1 | 0.0 | 0.0 | 32.2 | 0.0 | N/A |
| 79 | Qwen3-Coder 480B A35B Instruct qwen3-coder-480b-a35b-instruct codeprogrammingtool use | Alibaba Cloud / Qwen Team | 32.1 Programming | 0.0 | 0.0 | 50.7 | 32.1 | 0.0 | |
| 80 | Qwen3 Max qwen3-max codeprogrammingtool use | Alibaba Cloud / Qwen Team | 32.1 Programming | 28.0 | 0.0 | 0.0 | 32.1 | 0.0 | N/A |
61
DeepSeek-V3.2-Speciale
DeepSeek
42.0
N/A
62
Kimi K2.5
Moonshot AI
41.8
N/A
63
DeepSeek-V4-Flash-Max
DeepSeek
41.4
$0.1 in / $0.2 out
64