| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 161 | Muse Glimmer-30B muse-glimmer-30b multimodalvisionmulti-input reasoning | Meta | 40.1 overall | 42.2 | 15.0 | 49.7 | 38.6 | 54.7 | $0.3 in / $1.2 out |
| 162 | Gemini 2.5 Flash gemini-2.5-flash multimodalvisionmulti-input reasoning | Google | 39.0 overall | 36.9 | 66.7 | 0.0 | 19.6 | 42.9 | |
| 163 | Kimi K2 0905 kimi-k2-0905 textinference | Moonshot AI | 38.9 overall | 38.9 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 164 | LongCat-Flash-Lite longcat-flash-lite codeprogrammingtool use | Meituan | 38.9 overall | 21.7 | 75.2 | 30.1 | 23.6 | 83.7 | $0.1 in / $0.4 out |
| 165 | GLM-4.6 glm-4.6 multimodalvisionmulti-input reasoning | Zhipu AI | 38.5 overall | 42.9 | 26.2 | 34.8 | 42.6 | 46.2 | $0.5 in / $2 out |
| 166 | L3 8B Lunaris v1 l3-8b-lunaris-v1 textinference | Sao10K | 38.5 overall | 0.0 | 0.8 | 0.0 | 0.0 | 98.9 | $0.04 in / $0.05 out |
| 167 | DeepSeek-V3.2 deepseek-v3.2 codeprogrammingtool use | DeepSeek | 38.4 overall | 54.0 | 22.1 | 12.0 | 42.5 | 75.5 | $0.26 in / $0.38 out |
| 168 | DeepSeek-V3.2-Exp deepseek-v3.2-exp codeprogrammingtool use | DeepSeek | 38.4 overall | 48.7 | 0.0 | 27.1 | 37.5 | 0.0 | N/A |
| 169 | Gemini 2.5 Pro Preview 06-05 gemini-2.5-pro-preview-06-05 multimodalvisionmulti-input reasoning | Google | 38.2 overall | 48.5 | 0.0 | 0.0 | 25.1 | 0.0 | |
| 170 | MiniMax M2 minimax-m2 codeprogrammingtool use | MiniMax | 38.2 overall | 28.4 | 41.0 | 39.9 | 41.5 | 49.4 | $0.3 in / $1.2 out |
| 171 | Mistral Small 4 mistral-small-latest multimodalvisionmulti-input reasoning | Mistral AI | 37.8 overall | 29.9 | 30.9 | 0.0 | 0.0 | 70.9 | |
| 172 | Nemotron 3 Ultra (550B A55B) nemotron-3-ultra-550b-a55b codeprogrammingtool use | NVIDIA | 37.5 overall | 52.9 | 41.8 | 10.7 | 40.6 | 44.5 | $0.5 in / $2.2 out |
| 173 | GPT-5.3 Chat gpt-5.3-chat-latest multimodalvisionmulti-input reasoning | OpenAI | 37.1 overall | 0.0 | 46.0 | 0.0 | 0.0 | 23.0 | |
| 174 | LongCat-Flash-Thinking-2601 longcat-flash-thinking-2601 codeprogrammingtool use | Meituan | 37.0 overall | 50.7 | 0.0 | 25.7 | 31.8 | 0.0 | |
| 175 | Ling 3.0 Flash ling-3.0-flash codeprogrammingtool use | InclusionAI | 36.7 overall | 0.0 | 15.0 | 30.3 | 33.7 | 93.1 | $0.06 in / $0.18 out |
| 176 | MiMo-V2-Flash mimo-v2-flash codeprogrammingtool use | Xiaomi | 36.6 overall | 48.6 | 0.0 | 23.4 | 35.9 | 0.0 | N/A |
| 177 | o4-mini o4-mini multimodalvisionmulti-input reasoning | OpenAI | 36.6 overall | 44.6 | 0.0 | 35.3 | 27.7 | 0.0 | N/A |
| 178 | Grok Code Fast 1 grok-code-fast-1 codeprogrammingtool use | xAI | 36.1 overall | 0.0 | 30.8 | 0.0 | 34.7 | 47.7 | $0.2 in / $1.5 out |
| 179 | GLM-5 glm-5 codeprogrammingtool use | Zhipu AI | 36.0 overall | 0.0 | 8.2 | 35.6 | 60.5 | 27.3 | $1 in / $3.2 out |
| 180 | QvQ-72B-Preview qvq-72b-preview multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 35.9 overall | 35.9 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
161
Muse Glimmer-30B
Meta
40.1
$0.3 in / $1.2 out
162Google
Gemini 2.5 Flash
39.0
$0.3 in / $2.5 out
163
Kimi K2 0905
Moonshot AI
38.9
N/A
164