GPT 6 Sol
GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, reasoning, coding, and agentic workflows.
- Reasoning
- Vision
- Native PDF input
- Tool Calling
- Structured Output
Added Sep 22, 2026
Pricing
Auto routing · per 1M tokens- Input
- $2.00
- Output
- $10.00
- Cache read
- $0.20
Specifications
- Context window
- 1.1M
- Max output
- 128K
Benchmarks
Benchmarks
Sourced from Vectara.
Hallucination Rate
6.5%
Factual Consistency
93.5%
Answer Rate
100.0%
Avg Summary Length
Average generated summary length
71.4
Last updated 2026-10-22 · Matched as openai/gpt-6-sol
Vectara LeaderboardLeaderboard results
| Benchmark | Score | Rank on NanoGPT |
|---|---|---|
Epoch AI Benchmarking Hub Epoch AI data, CC BY 4.0 · Updated Nov 22, 2026 | ||
Epoch Capabilities Index | 163.8 | #14 of 114 |
FrontierMath v2 (Tiers 1–3) | 89.8% | #10 of 84 |
GPQA Diamond | 94.3% | #12 of 119 |
SimpleQA Verified | 60.7% | #21 of 84 |
FrontierMath v2 (Tier 4) | 90.0% | #10 of 68 |
OTIS Mock AIME 2024–2025 | 100.0% | #11 of 121 |
MirrorCode | 48.9% | #19 of 41 |
Chess Puzzles | 56.0% | #15 of 83 |
Mystery Game Puzzles | 56.0% | #16 of 80 |
Creative Writing v3 | 2126 | #5 of 91 |
Longform Writing | 82.8 | #7 of 93 |
UGI Leaderboard UGI Leaderboard data, Apache-2.0 · Updated Nov 22, 2026 | ||
UGI Score | 57.8 | #11 of 125 |
UGI Willingness | 2.8 | #68 of 125 |
UGI Writing | 55.6 | #46 of 125 |
Filtered and ranked to models on NanoGPT.
Providers
Auto routing is available for this model. Explicit provider selection is not available.
| Cache write /M | ||||||
|---|---|---|---|---|---|---|
Recommended | $2.00 | $10.00 | $0.20 | $2.50 | N/A | N/A |
| >272k | $4.00 | $15.00 | $0.40 | $5.00 |