| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 221 | GPT-5.4 nano gpt-5.4-nano multimodalvisionmulti-input reasoning | OpenAI | 29.4 overall | 38.1 | 52.5 | 6.9 | 13.3 | 57.1 | $0.2 in / $1.25 out |
| 222 | IBM Granite 4.2 30B granite-4.2-30b codeprogrammingtool use | IBM | 29.4 overall | 34.2 | 15.0 | 0.0 | 16.0 | 68.1 | $0.16 in / $0.65 out |
| 223 | L3.1 70B Euryale v2.2 l3.1-70b-euryale-v2.2 textinference | Sao10K | 29.2 overall | 0.0 | 15.0 | 0.0 | 0.0 | 51.9 | $0.85 in / $0.85 out |
| 224 | Qwen3 235B A22B qwen3-235b-a22b multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 29.0 overall | 29.0 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 225 | Hermes 3 70B hermes-3-70b textinference | Nous Research | 28.6 overall | 25.8 | 15.0 | 0.0 | 0.0 | 58.2 | $0.7 in / $0.7 out |
| 226 | Ministral 3 (8B Reasoning 2512) ministral-8b-latest multimodalvisionmulti-input reasoning | Mistral AI | 28.5 overall | 28.5 | 0.0 | 0.0 | 0.0 | 0.0 | |
| 227 | Qwen3 Max qwen3-max codeprogrammingtool use | Alibaba Cloud / Qwen Team | 28.5 overall | 26.8 | 30.9 | 0.0 | 30.6 | 25.0 | $1.2 in / $6 out |
| 228 | GPT-5.2 Codex gpt-5.2-codex multimodalvisionmulti-input reasoning | OpenAI | 28.5 overall | 0.0 | 32.9 | 0.0 | 31.8 | 14.5 | $1.75 in / $14 out |
| 229 | DeepSeek-V3.1 deepseek-v3.1 codeprogrammingtool use | DeepSeek | 28.4 overall | 35.2 | 22.1 | 13.3 | 25.1 | 62.9 | $0.25 in / $0.95 out |
| 230 | Llama 3.3 70B Instruct llama-3.3-70b-instruct textinference | Meta | 28.4 overall | 16.5 | 15.0 | 0.0 | 0.0 | 83.2 | $0.1 in / $0.32 out |
| 231 | Qwen3.5-4B qwen3.5-4b multimodalvisionmulti-input reasoning | Alibaba Cloud / Qwen Team | 28.3 overall | 28.3 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 232 | Qwen3 32B qwen3-32b textinference | Alibaba Cloud / Qwen Team | 28.3 overall | 20.0 | 7.1 | 0.0 | 0.0 | 85.7 | $0.08 in / $0.28 out |
| 233 | IBM Granite 4.2 8B granite-4.2-8b codeprogrammingtool use | IBM | 28.2 overall | 30.1 | 15.0 | 0.0 | 8.4 | 87.4 | $0.06 in / $0.25 out |
| 234 | Hermes 3 405B hermes-3-405b textinference | Nous Research | 28.2 overall | 0.0 | 15.0 | 0.0 | 0.0 | 49.2 | $1 in / $1 out |
| 235 | GPT-4.5 gpt-4.5 multimodalvisionmulti-input reasoning | OpenAI | 28.1 overall | 40.1 | 0.0 | 35.8 | 4.5 | 0.0 | N/A |
| 236 | Phi 4 Reasoning Plus phi-4-reasoning-plus textinference | Microsoft | 28.1 overall | 28.1 | 0.0 | 0.0 | 0.0 | 0.0 | N/A |
| 237 | GPT-4o gpt-4o-2024-05-13 multimodalvisionmulti-input reasoning | OpenAI | 28.0 overall | 18.7 | 46.0 | 0.0 | 0.0 | 25.2 | $2.5 in / $10 out |
| 238 | Mistral Small 3.2 24B Instruct mistral-small-3.2-24b-instruct-2506 multimodalvisionmulti-input reasoning | Mistral AI | 27.7 overall | 17.3 | 7.1 | 0.0 | 0.0 | 89.6 | |
| 239 | Command A+ command-a-plus-05-2026 multimodalvisionmulti-input reasoning | Cohere | 27.4 overall | 33.8 | 0.0 | 0.0 | 19.2 | 0.0 | |
| 240 | Claude 3.5 Sonnet claude-3-5-sonnet-20241022 multimodalvisionmulti-input reasoning | Anthropic | 27.1 overall | 30.3 | 0.0 | 38.7 | 10.3 | 0.0 |
221
GPT-5.4 nano
OpenAI
29.4
$0.2 in / $1.25 out
222
IBM Granite 4.2 30B
IBM
29.4
$0.16 in / $0.65 out
223
L3.1 70B Euryale v2.2
Sao10K
29.2
$0.85 in / $0.85 out
224