GPT-6.2 Sol
Released 17 Nov 2026proprietaryAlso written as GPT-6.2 Sol, gpt-6-2-sol, openai/gpt-6.2-sol
4 results on 4 of 14 boards, latest measured Nov 2026. Compare with other models
On the Clinical Benchmarks Index
The top 15 on the index.The top 10 on the index. Select a column to open that model.
Board by board
Leading models on each board, with GPT-6.2 Sol included, on that board's own scale. Its own column is in colour.
HealthBench Professionalrank 6 of 46
- 0.703GPT-6 Astra (Anthropic run)
- 0.692Claude Sonnet 5.5
- 0.677Claude Fable 5.2
- 0.663GPT-6.2 Astra
- 0.660Claude Fable 5
- 0.659GPT-6.2 Sol
- 0.656Claude Opus 5.5
- 0.655GPT-6 Luna (Anthropic run)
- 0.648Claude Haiku 5.5
- 0.642GPT-6.1 Sol
Top 10 of 40 modelsFull board
MLCR-AArank 7 of 30
- 43.9Claude Fable 5.2
- 41.7Claude Sonnet 5.5 (Max, Default Fallback)
- 41.7GPT-6 Astra (Max)
- 39.4GPT-6.2 Astra
- 38.3GPT-6.1 Sol (Max)
- 38.3Kimi K3.1 Pro
- 37.2GPT-6.2 Sol
- 35.0Claude Haiku 5.5 (Max)
- 33.9GPT-6 Sol (Max)
- 31.7GPT-5.5 Instant (June 2026)
Top 10 of 30 modelsFull board
RCM-Benchrank 21 of 22
- 92.68Claude Opus 5
- 91.49Gemini 4 Argon
- 91.24Claude Sonnet 5
- 91.21GPT-5.6 Sol
- 91.05Claude Sonnet 5.5
- 90.23Gemini 3.8 Flash
- 90.14Claude Opus 5.5
- 89.82Claude Sonnet 4.6
- 88.99DeepSeek V4.1 Flash
- 71.2GPT-6.2 Sol
Top 9 of 22 models, plus this modelFull board
DAYJOB Healthrank 13 of 18
- 48.3Claude Opus 5.5
- 45.0Claude Fable 5.2
- 34.4GPT-6.2 Astra
- 34Claude Sonnet 5.5
- 31.2Claude Fable 5.1
- 31.2Muse Wonder 1.0
- 28.4GPT-6 Astra
- 27.6Grok 4.7
- 25.2GPT-6.1 Sol
- 17.2GPT-6.2 Sol
Top 9 of 18 models, plus this modelFull board
Every result, with its source
Each line sits on its own board's scale. Tall tick: the board leader.
Clinical reasoning and knowledge
- HealthBench ProfessionalOpenAI; length-adjusted; reasoning effort not stated in the card; raw 65.5; 1,869 mean response characters0.659Rank 6 of 46Leader GPT-6 Astra (Anthropic run) 0.703
Documentation and coding
- MLCR-AAoverall pass rate, Max37.2Rank 7 of 30 here, 27 models on the boardLeader Claude Fable 5.2 43.9
EHR and workflow agents
- RCM-BenchScore (avg@3), medium reasoning71.2Rank 21 of 22 here, 20 models on the boardLeader Claude Opus 5 92.68
- DAYJOB HealthScore (pass@1 at 95%), reasoning max17.2Rank 13 of 18 here, 15 models on the boardLeader Claude Opus 5.5 48.3
Index working
Show the working: each board’s result, how hard the board runs and the field average
The Clinical Benchmarks Index is this site's own calculation from 12 boards. How it is computed
- HealthBench Professional0.65965.9+5.0 easy board60.90.743 weightOpenAI; length-adjusted; reasoning effort not stated in the card; raw 65.5; 1,869 mean response characters
- RCM-Bench71.271.2+34.6 easy board36.60.088 weight, near its ceilingNear its ceiling: leader 92.7, weight 0.088Score (avg@3), medium reasoning
- DAYJOB Health17.217.2−29.6 hard board46.80.6 weightScore (pass@1 at 95%), reasoning max
- MLCR-AA37.237.2−25.9 hard board63.10.6 weightoverall pass rate, Max
- Adjusted average of 4 boards, by weight
- 56.3
- Field average, counts for 27.3% with 4 of 12 boards
- 44.9
- Index
- = 53.2
Score: the result on the board’s own 0 to 100 scale (dot; tick: the board’s leader). Board runs: how far the board’s scores sit above or below the same models’ scores on the other boards. Adjusted: the score minus that offset. The index is the adjusted average with the field average mixed in, more of it the fewer boards a model has. Each result links to its quote and page; the line under it is the setting it was measured with.
Sources
The quote, page and document for each of the 4 results
6HealthBench Professional length-adjusted 0.659
Printed as 65.9Vendor-reported, measured Nov 2026Configuration: OpenAI; length-adjusted; reasoning effort not stated in the card; raw 65.5; 1,869 mean response charactersGPT-6.2 Astra and Sol System Card system card, OpenAI, 17 Nov 2026. PDF p. 74 (printed p. 73), section 3.4.1, Table 17GPT-6.2 Astra and GPT-6.2 Sol scored 66.3 and 65.9 after adjustment
Every result from this document21RCM-Bench Score 71.2
Printed as 71.2%Official leaderboard, measured Nov 2026Configuration: Score (avg@3), medium reasoningRCM-Bench-1 on the Fireworks Specialized Intelligence Index official leaderboard, Fireworks AI, 22 Oct 2026. leaderboard row 26, read 2026-11-2126 GPT-6.2 Sol OpenAI 71.2% $0.12
Every result from this document13DAYJOB Health Score 17.2
Printed as 17.2%Official leaderboard, measured Nov 2026Configuration: Score (pass@1 at 95%), reasoning maxDAYJOB: Healthcare leaderboard official leaderboard, Surge AI. DAYJOB Healthcare leaderboard, rank 17, read 2026-11-21GPT 6.2 Sol (Max) 17.2 %
Every result from this document7MLCR-AA overall pass rate 37.2
Printed as 37.2%Independent run, measured Nov 2026Configuration: overall pass rate, MaxMLCR-AA (Medical Long Context Reasoning), Artificial Analysis official leaderboard, Artificial Analysis, 5 Nov 2026. Score chart data, record "GPT-6.2 Sol (Max)", field mlcrOverall (a fraction, charted as a percent)"mlcrOverall":0.372222222222222
Every result from this document
Other OpenAI models: GPT-5, GPT-5.1, GPT-5.2, GPT-5.3-Codex, GPT-5.4, GPT-5.4 mini, GPT-5.4 nano, GPT-5.5, GPT-5.5 Instant, GPT-5.6 Luna, GPT-5.6 Sol, GPT-5.6 Terra, GPT-5 mini, GPT-5 nano, GPT-6.1 Sol, GPT-6.1 Terra, GPT-6.2 Astra, GPT-6 Astra, GPT-6 Luna, GPT-6 Sol, o3, o4-mini