| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 241 | GPT-4.1 mini gpt-4.1-mini-2025-04-14 multimodalvisionmulti-input reasoning | OpenAI | 26.6 overall | 17.8 | 83.7 | 8.9 | 1.9 | 56.9 | $0.4 in / $1.6 out |
| 242 | MythoMax L2 13B mythomax-l2-13b textinference | Gryphe | 26.5 overall | 0.0 | 0.0 | 0.0 | 0.0 | 69.0 | $0.4 in / $0.4 out |
| 243 | Mistral Large 3 (675B Instruct 2512) mistral-large-latest multimodalvisionmulti-input reasoning | Mistral AI | 26.4 overall | 21.8 | 24.1 | 0.0 | 0.0 | 43.1 | |
| 244 | Nemotron 3.5 Lightning (30B A3B) nemotron-3.5-lightning-30b-a3b codeprogrammingtool use | NVIDIA | 26.3 overall | 26.3 | 41.8 | 6.4 | 8.2 | 89.0 | $0.08 in / $0.2 out |
| 245 | Gemma 3 12B gemma-3-12b-it multimodalvisionmulti-input reasoning | Google | 26.3 overall | 8.0 | 15.0 | 0.0 | 0.0 | 95.6 | $0.05 in / $0.15 out |
| 246 | Qwen3 VL 8B Thinking qwen3-vl-8b-thinking multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 26.1 overall | 31.6 | 0.0 | 19.7 | 0.0 | 0.0 | N/A |
| 247 | Pixtral Large pixtral-large multimodalvisionmulti-input reasoning | Mistral AI | 26.1 overall | 26.1 | 0.0 | 0.0 | 0.0 | 0.0 | |
| 248 | Kimi K2 Base kimi-k2-base textinference | Moonshot AI | 25.5 overall | 25.5 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 249 | MiniCPM-SALA minicpm-sala textinference | OpenBMB | 25.5 overall | 25.5 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 250 | Qwen3 14B qwen3-14b textinference | Alibaba Cloud / Qwen Team | 25.4 overall | 15.8 | 3.8 | 0.0 | 0.0 | 86.5 | $0.12 in / $0.24 out |
| 251 | Gemma 3 27B gemma-3-27b-it multimodalvisionmulti-input reasoning | Google | 25.4 overall | 7.1 | 15.0 | 0.0 | 0.0 | 93.1 | $0.08 in / $0.16 out |
| 252 | Mistral Small 3 24B Instruct mistral-small-24b-instruct-2501 textinference | Mistral AI | 25.2 overall | 11.9 | 3.0 | 0.0 | 0.0 | 97.8 | $0.05 in / $0.08 out |
| 253 | o1-preview o1-preview codeprogrammingtool use | OpenAI | 25.1 overall | 39.2 | 0.0 | 0.0 | 7.1 | 0.0 | N/A |
| 254 | GPT OSS 20B gpt-oss-20b textinference | OpenAI | 25.1 overall | 22.0 | 15.0 | 6.0 | 0.0 | 96.2 | $0.03 in / $0.14 out |
| 255 | Phi 4 phi-4 textinference | Microsoft | 25.0 overall | 13.4 | 1.6 | 0.0 | 0.0 | 94.5 | $0.07 in / $0.14 out |
| 256 | GPT-4 Turbo gpt-4-turbo-2024-04-09 textinference | OpenAI | 24.9 overall | 14.2 | 49.2 | 0.0 | 0.0 | 15.8 | $10 in / $30 out |
| 257 | Qwen3 VL 30B A3B Thinking qwen3-vl-30b-a3b-thinking multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 24.7 overall | 30.8 | 0.0 | 17.5 | 0.0 | 0.0 | |
| 258 | DeepSeek R1 Distill Llama 70B deepseek-r1-distill-llama-70b textinference | DeepSeek | 24.7 overall | 24.7 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 259 | QwQ-32B qwq-32b textinference | Alibaba Cloud / Qwen Team | 24.7 overall | 24.7 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 260 | QwQ-32B-Preview qwq-32b-preview textinference | Alibaba Cloud / Qwen Team | 24.7 overall | 24.7 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
241
GPT-4.1 mini
OpenAI
26.6
$0.4 in / $1.6 out
242
MythoMax L2 13B
Gryphe
26.5
$0.4 in / $0.4 out
243
Mistral Large 3 (675B Instruct 2512)
Mistral AI
26.4
$0.5 in / $1.5 out
244