GPT-6.1 Sol
Category scores
Scores per capability area with the model's rank among ranked models in that category.
- 1Math97.3
- 2Reasoning#290.5
- 3Multimodal87.3
- 4Knowledge#483.8
- 5Coding#874.1
Benchmark results (25)
As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.
Agentic & tool use
| MazeBench | 17 | #2 of 42 |
| AutomationBench | 36.1 | #15 of 25 |
| Hermes Index | 57.1 | #2 of 16 |
| Hermes Bench | 73.9 | #3 of 16 |
| ExploitGym | 35.1 | #2 of 14 |
| Terminal-Bench-Science 0.1 | 57.0 | #4 of 5 |
Reasoning
| ARC-AGI-2 | 94.2 | #2 of 41 |
| ARC-AGI-1 | 96.50 | #8 of 36 |
| ARC-AGI-3 | 52.7 | #2 of 22 |
| STEMBench | 2.76 | #2 of 9 |
| ARC-AGI-3 Provider Adapter | 96.18 | #3 of 8 |
Knowledge
| HealthBench Professional | 64.2 | #5 of 16 |
| HealthBench Hard | 36.2 | #4 of 12 |
| HealthBench (raw) | 56.7 | #5 of 7 |
| HealthBench (length-adjusted) | 58.5 | #3 of 7 |
| HealthBench Professional (raw) | 67.2 | #5 of 7 |
Multimodal
| Design Arena Website | 1321 | #7 of 91 |
| ParseBench | 70.48 | #12 of 37 |
| ExtractBench Pro | 12 | #4 of 5 |
Coding
| DeepSWE | 71.9 | #14 of 50 |
| Bug Hunt Bench | 44.3 | #3 of 23 |
Math
| FrontierMath v2 (Tiers 1-3) | 93.684 | #1 of 64 |
| FrontierMath v2 (Tier 4) | 100.000 | #1 of 51 |
Pricing by source
USD per 1M tokens.
| Source | Input | Output | Cached in |
|---|---|---|---|
| ✓ Official (OpenAI) checked Oct 17, 2026 · gpt-6.1-sol | $2.00 | $10.00 | $0.10 |
| BenchLM list price | $2.00 | $10.00 | $0.10 |
| OpenRouter openai/gpt-6.1-sol | $2.00 | $10.00 | $0.10 |
Standard tier, prompts under 272K tokens.
OpenAI's GPT-6.1 Sol model page lists $2.00 input / $0.10 cached input / $2.50 cache writes / $10.00 output per million tokens. Prompts above 272K input tokens are charged at 2x input and cache rates and 1.5x output for the full request; regional processing adds 10% where available; Batch and Flex are 50% of Standard and Fast mode is 2x.
Arena ratings
Human-preference ratings from LMArena. Best-rated variant shown.
| Text(max) | 1448 | #57 · 6.3K votes |
| WebDev (coding)(Max) | 1753 | #4 · 3.1K votes |
| Vision(Max) | 1288 | #29 · 2.3K votes |
| Search(max) | 1233 | #8 · 5.6K votes |
Speed
Measured by us through OpenRouter (median of trials).
Not measured yet.
Related models
Same family
- GPT-6 Astra84.0
- GPT-6 Sol78.6
- GPT-6 Luna66.6
Similar score
- GPT-6 Astra84.0 · $20.00
- Claude Fable 5.183.2 · $20.00
- Gemini 4 Argon82.9 · $4.00
- Claude Sonnet 5.582.2 · $4.00
- Claude Opus 5.586.7 · $8.00