| Rank | Model | Provider | Score | Benchmarks | Inference | Agentic | Programming | Value | Price |
|---|---|---|---|---|---|---|---|---|---|
| 21 | GLM-5.1 glm-5.1 codeprogrammingtool use | Zhipu AI | 58.3 Programming | 67.1 | 46.6 | 54.4 | 58.3 | 30.6 | $1.4 in / $4.4 out |
| 22 | Gemini 3 Pro gemini-3-pro-preview multimodalvisionmulti-input reasoning | Google | 57.4 Programming | 73.3 | 0.0 | 63.8 | 57.4 | 0.0 | |
| 23 | Claude Haiku 4.5 claude-haiku-4-5-20251001 multimodalvisionmulti-input reasoning | Anthropic | 57.2 Programming | 32.9 | 61.2 | 54.2 | 57.2 | 37.7 | |
| 24 | GPT-5.1 gpt-5.1-2025-11-13 multimodalvisionmulti-input reasoning | OpenAI | 57.2 Programming | 65.0 | 71.4 | 0.0 | 57.2 | 31.9 | |
| 25 | GPT-5.1 Instant gpt-5.1-instant-2025-11-12 multimodalvisionmulti-input reasoning | OpenAI | 57.2 Programming | 65.0 | 71.4 | 0.0 | 57.2 | 31.9 | |
| 26 | GPT-5.1 Thinking gpt-5.1-thinking-2025-11-12 multimodalvisionmulti-input reasoning | OpenAI | 57.2 Programming | 65.0 | 55.1 | 0.0 | 57.2 | 27.0 | |
| 27 | MiniMax M2.5 minimax-m2.5 codeprogrammingtool use | MiniMax | 56.3 Programming | 0.0 | 73.9 | 53.0 | 56.3 | 57.7 | $0.3 in / $1.2 out |
| 28 | MiMo-V2-Omni mimo-v2-omni multimodalvisionmulti-input reasoning | Xiaomi | 55.6 Programming | 0.0 | 59.2 | 0.0 | 55.6 | 44.7 | $0.4 in / $2 out |
| 29 | GPT-5 Codex gpt-5-codex-2025-09-15 codeprogrammingtool use | OpenAI | 54.3 Programming | 0.0 | 0.0 | 0.0 | 54.3 | 0.0 | N/A |
| 30 | Step-3.5-Flash step-3.5-flash codeprogrammingtool use | StepFun | 53.0 Programming | 62.3 | 63.2 | 45.3 | 53.0 | 82.1 | $0.1 in / $0.4 out |
| 31 | GPT-5 gpt-5-2025-08-07 multimodalvisionmulti-input reasoning | OpenAI | 51.7 Programming | 64.4 | 0.0 | 29.0 | 51.7 | 0.0 | |
| 32 | GPT-5.1 Codex gpt-5.1-codex multimodalvisionmulti-input reasoning | OpenAI | 51.2 Programming | 0.0 | 48.6 | 0.0 | 51.2 | 25.1 | |
| 33 | MiniMax M2.1 minimax-m2.1 codeprogrammingtool use | MiniMax | 50.6 Programming | 42.7 | 73.9 | 56.6 | 50.6 | 57.7 | $0.3 in / $1.2 out |
| 34 | Seed 2.0 Lite seed-2.0-lite multimodalvisionmulti-input reasoning | ByteDance | 50.3 Programming | 58.1 | 0.0 | 0.0 | 50.3 | 0.0 | N/A |
| 35 | Claude Opus 4 claude-opus-4-20250514 multimodalvisionmulti-input reasoning | Anthropic | 49.5 Programming | 37.8 | 0.0 | 57.9 | 49.5 | 0.0 | |
| 36 | GPT-5.3 Codex gpt-5.3-codex texttext-to-textcoding | OpenAI | 49.3 Programming | 0.0 | 48.6 | 0.0 | 49.3 | 19.5 | |
| 37 | Kimi K2.5 kimi-k2.5 multimodalvisionmulti-input reasoning | Moonshot AI | 48.5 Programming | 68.0 | 66.8 | 49.5 | 48.5 | 38.1 | |
| 38 | GLM-4.6 glm-4.6 multimodalvisionmulti-input reasoning | Zhipu AI | 46.1 Programming | 47.0 | 34.9 | 37.7 | 46.1 | 42.8 | $0.55 in / $2.19 out |
| 39 | DeepSeek-V3.2 (Thinking) deepseek-reasoner codeprogrammingtool use | DeepSeek | 45.9 Programming | 53.1 | 0.0 | 16.6 | 45.9 | 0.0 | |
| 40 | DeepSeek-V3.2 deepseek-v3.2 codeprogrammingtool use | DeepSeek | 45.9 Programming | 58.1 | 52.5 | 16.6 | 45.9 | 70.0 | $0.26 in / $0.38 out |
21
GLM-5.1
Zhipu AI
58.3
$1.4 in / $4.4 out
22Google
Gemini 3 Pro
57.4
N/A
23
Claude Haiku 4.5
Anthropic
57.2
$1 in / $5 out
24