OpenAIGPT-6.1 Sol
GPT-6.1 Sol is an OpenAI proprietary reasoning model, released 29 Sept 2026. Its best configuration (max reasoning effort) ranks #10 of 760 on the BenchLeader Index at 69.3 ±3.2, in the top ten. The ± is the point: 48 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in composite (79) and lowest in agents & tools (64). At $4.00 per million tokens blended it is among the most expensive ranked models. Output speed of 56 tokens per second puts it slower than most, with a first answer in 326.9 s. It has been measured at 6 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 9 Oct 2026.
- Blended price
- $4.00/M
- $2.00 in · $10.00 out
- Output speed
- 56 tok/s
- measured by Artificial Analysis
- First answer
- 327 s
- first token 5.01 s
- Context
- 1.1M
- Full answer
- 336 s
- median, reasoning included
- Cost per run
- $0.724
- one full Intelligence Index run
- Released
- 29 Sept 2026
- Overall index69
- Reasoning76
- Coding72
- Agents & tools64
- Maths73
- Knowledge79
- Human preference68
- Multimodal66
- Long context67
- Composite79
Versions
OpenAI has shipped 3 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| GPT-6.1 Solmaxthis page | 29 Sept 2026 | 69.3 | #10 |
| GPT-6 Solmax | 22 Sept 2026 | 65.6 | #35 |
| GPT-5.6 Solmax | 9 Jul 2026 | 67.5 | #22 |
Reasoning-effort configurations
The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Not stated” collects results from publishers that did not say which setting they used; for a reasoning model that is usually its thinking mode, but we do not assume it. Pick a setting here or at the top of the page to see its price, speed and category scores.
| Effort | Index | Rank | Speed | First answer | Chat reply cost | Categories |
|---|---|---|---|---|---|---|
| low | 65.2 | #40 | 47 tok/s | 2.80 s | $0.0038 | Coding 59 · Composite 77 · Knowledge 79 · Long context 67 · Multimodal 66 · Reasoning 73 |
| medium | 67.5 | #24 | 49 tok/s | 5.76 s | $0.0038 | Coding 62 · Composite 84 · Knowledge 80 · Long context 67 · Multimodal 67 · Reasoning 77 |
| high | 67.9 | #16 | 50 tok/s | 60 s | $0.0038 | Coding 63 · Composite 87 · Knowledge 80 · Long context 66 · Multimodal 68 · Reasoning 79 |
| xhigh | 67.2 | #25 | 53 tok/s | 152 s | $0.0038 | Coding 63 · Composite 78 · Knowledge 80 · Long context 65 · Multimodal 68 · Reasoning 80 |
| maxbest | 69.3 | #10 | 56 tok/s | 327 s | $0.0038 | Agents & tools 64 · Coding 72 · Composite 79 · Human preference 68 · Knowledge 79 · Long context 67 · Maths 73 · Multimodal 66 · Reasoning 76 |
| not stated | – | – | 35 tok/s | 5.01 s | $0.0038 | Instruction following 83 · Knowledge 56 · Maths 79 |
What more thinking costs
Turning the effort up buys index points and multiplies the bill. Here max costs 5.5× low for +4.1 on the index — 1.7 points per doubling of spend. Compare that with other models.
How its index has moved
2 Oct 2026 to 9 Oct 2026- max
- high
- medium
- xhigh
The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|
| GPQA Diamond | – | – | – | – | 95.4%#3 | – | Epoch AI Benchmarking Hub | |
| LMArena Hard Prompts | – | – | – | – | 1507#19 | – | LMArena | |
| LiveBench Reasoningnot in index | – | – | – | 91.6%#6 | 92.6%#2 | – | LiveBench | |
| Humanity's Last Exam (AA)not in index | 47.4%#36 | 49.9%#24 | 51.4%#21 | 52.6%#20 | 52.9%#17 | – | Artificial Analysis | |
| ARC-AGI-1 | 93.5%#44 | 95.5%#29 | 98.5%#1 | 98.5%#1 | 96.5%#21 | – | ARC Prize | |
| ARC-AGI-2 | 76.7%#44 | 86.7%#24 | 91.7%#9 | 91.7%#9 | 94.2%#2 | – | ARC Prize | |
| ARC-AGI-3 | 82.8%#11 | 91.0%#10 | 95.0%#9 | 96.4%#7 | 96.2%#8 | – | ARC Prize | |
| CritPt | 24.9%#42 | 27.7%#27 | 30.0%#15 | 31.7%#2 | 31.7%#2 | – | Artificial Analysis | |
| MysteryMechanismnot in index | – | – | – | – | 46.4%#5 | – | Vals AI | |
| Chess Puzzlesnot in index | – | – | – | – | 61.0%#4 | – | Epoch AI Benchmarking Hub | |
| Mystery Game Puzzlesnot in index | – | – | – | – | 80.0%#2 | – | Epoch AI Benchmarking Hub |
Coding
| Benchmark | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|
| SciCode | 53.2%#73 | 53.2%#73 | 55.8%#40 | 55.7%#41 | 54.2%#59 | – | SciCode | |
| FrontierCode | – | 50.2%#7 | – | – | – | – | Cognition | |
| LMArena Coding | – | – | – | – | 1545#8 | – | LMArena | |
| LMArena WebDev | – | – | – | – | 1755#4 | – | LMArena | |
| LiveBench Codingnot in index | – | – | – | 80.7%#17 | 80.4%#19 | – | LiveBench | |
| SciCode (AA)not in index | 53.2%#73 | 53.2%#73 | 55.8%#40 | 55.7%#42 | 54.2%#61 | – | Artificial Analysis | |
| IOI | – | – | – | – | 96.9%#3 | – | Vals AI | |
| Code Migrationnot in index | – | – | – | – | 65.1%#5 | – | Vals AI | |
| Vibe Code Bench v1.1not in index | – | – | – | – | 88.9%#7 | – | Vals AI | |
| Terminal-Bench 4.0 (AA)not in index | 30.8%#41 | 48.0%#19 | 51.5%#16 | 54.0%#11 | 56.1%#9 | – | Artificial Analysis |
Agents & tools
| Benchmark | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|
| Terminal-Bench | – | – | – | – | 58.2%#17 | – | Terminal-Bench | |
| APEX-Agents | – | – | – | – | 60.0%#12 | – | Mercor | |
| LMArena Agent | – | – | – | – | 11.7#5 | – | LMArena | |
| LiveBench Agentic Codingnot in index | – | – | – | 56.8%#24 | 54.5%#31 | – | LiveBench | |
| GDPval-AA v2.1not in index | 39.9%#97 | 46.6%#62 | 49.3%#48 | 50.5%#44 | 53.8%#35 | – | Artificial Analysis | |
| Analyst Agent (AA)not in index | – | – | – | – | 50.0%#7 | – | Artificial Analysis | |
| CyberBenchnot in index | – | – | – | – | 39.3%#39 | – | Vals AI | |
| Finance Agent v2not in index | – | – | – | – | 52.0%#30 | – | Vals AI | |
| Harvey's Legal Agent Benchmarknot in index | – | – | – | – | 5.4%#28 | – | Vals AI | |
| Legal Research Benchnot in index | – | – | – | – | 38.5%#27 | – | Vals AI | |
| SREBenchnot in index | – | – | – | – | 50.8%#2 | – | Vals AI | |
| Tax Agent Benchnot in index | – | – | – | – | 62.3%#26 | – | Vals AI | |
| Terminal-Bench 4.0 (Vals)not in index | – | – | – | – | 55.0%#6 | – | Vals AI | |
| AutomationBenchnot in index | – | – | 64.5%#16 | 66.6%#10 | 64.9%#14 | – | Artificial Analysis | |
| GDP.pdfnot in index | – | – | 32.0%#2 | 31.8%#3 | 31.0%#4 | – | Artificial Analysis | |
| Harvey LABnot in index | – | – | – | – | 6.9%#4 | – | Harvey | |
| AA-Briefcase v1.1not in index | – | – | 1465#29 | 1503#25 | 1557#16 | – | Artificial Analysis |
Maths
| Benchmark | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|
| FrontierMath Tiers 1–3 | – | – | – | – | 93.7%#1 | – | Epoch AI Benchmarking Hub | |
| FrontierMath Tier 4 | – | – | – | – | 100.0%#1 | – | Epoch AI Benchmarking Hub | |
| OTIS Mock AIME | – | – | – | – | 100.0%#1 | – | Epoch AI Benchmarking Hub | |
| ProofBencheffort not stated | – | – | – | – | – | 99.0%#4 | Vals AI | |
| LiveBench Mathematicsnot in index | – | – | – | 96.5%#7 | 96.8%#3 | – | LiveBench | |
| LMArena Maths | – | – | – | – | 1488#29 | – | LMArena |
Knowledge
| Benchmark | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|
| SimpleQA Verified | – | – | – | – | 73.9%#2 | – | Epoch AI Benchmarking Hub | |
| LiveBench Data Analysisnot in index | – | – | – | 82.2%#3 | 82.7%#2 | – | LiveBench | |
| AA-Omniscience | 37.6#20 | 40.0#18 | 41.5#12 | 40.9#13 | 41.5#11 | – | Artificial Analysis | |
| PRBench Financeeffort not stated | – | – | – | – | – | 46.2%#17 | Scale AI SEAL | |
| PRBench Legaleffort not stated | – | – | – | – | – | 47.9%#15 | Scale AI SEAL | |
| BioMysteryBenchnot in index | – | – | – | – | 79.6%#2 | – | Vals AI | |
| Excel Modeling Benchmarknot in index | – | – | – | – | 70.8%#12 | – | Vals AI | |
| MedCodenot in index | – | – | – | – | 48.8%#26 | – | Vals AI | |
| MedScribenot in index | – | – | – | – | 86.5%#21 | – | Vals AI | |
| Public Benefits Benchnot in index | – | – | – | – | 59.3%#30 | – | Vals AI | |
| EBR-benchnot in index | – | – | – | – | 54.3%#4 | – | Epoch AI Benchmarking Hub | |
| AA-Omniscience: accuracynot in index | 58.9%#25 | 60.4%#19 | 60.8%#17 | 60.8%#16 | 62.1%#12 | – | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 48.4%#120 | 48.4%#121 | 50.6%#107 | 49.1%#114 | 45.7%#135 | – | Artificial Analysis |
Instruction following
| Benchmark | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|
| LiveBench Languagenot in index | – | – | – | 88.7%#6 | 90.1%#2 | – | LiveBench | |
| LiveBench Instruction Followingnot in index | – | – | – | 71.3%#24 | 74.2%#12 | – | LiveBench | |
| MultiChallengeeffort not stated | – | – | – | – | – | 82.0%#1 | Scale AI SEAL | |
| LMArena Instruction Followingnot in index | – | – | – | – | 1488#15 | – | LMArena |
Human preference
| Benchmark | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|
| LMArena Text | – | – | – | – | 1484#21 | – | LMArena | |
| LMArena Creative Writingnot in index | – | – | – | – | 1462#26 | – | LMArena | |
| LMArena Multi-turnnot in index | – | – | – | – | 1487#25 | – | LMArena | |
| LMArena Longer Queriesnot in index | – | – | – | – | 1496#20 | – | LMArena |
Multimodal
| Benchmark | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|
| LMArena Vision | – | – | – | – | 1288#30 | – | LMArena | |
| MMMU-Pro | 83.1%#27 | 83.9%#23 | 84.9%#13 | 85.1%#11 | 86.0%#6 | – | Artificial Analysis | |
| SAGEnot in index | – | – | – | – | 46.5%#35 | – | Vals AI |
Long context
| Benchmark | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|
| AA-LCR | 84.0%#11 | 83.3%#19 | 82.3%#37 | 79.7%#83 | 83.0%#24 | – | Artificial Analysis | |
| MLCRnot in index | – | – | – | – | 33.9%#15 | – | Artificial Analysis |
Composite
| Benchmark | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|
| Epoch Capabilities Indexnot in indexeffort not stated | – | – | – | – | – | 166.1#3 | Epoch AI Benchmarking Hub | |
| LiveBench | – | – | – | 81.1%#8 | 81.6%#6 | – | LiveBench | |
| AA Intelligence Index v4.3.2 | 42.1#49 | 47.8#24 | 50.2#17 | 51.0#14 | 51.8#11 | – | Artificial Analysis | |
| Vals Indexnot in index | – | – | – | – | 61.1#8 | – | Vals AI |
Where it wins
Benchmarks where this configuration ranks in the top five of every configuration measured.
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| OpenAI | 84 tok/s | 2.35 s | $12.00 | $60.00 | 1.1M | – |
| Amazon Bedrock | 46 tok/s | 1.92 s | $2.20 | $11.00 | 1.1M | – |
| Azure | 45 tok/s | 1.93 s | $2.20 | $11.00 | 1.1M | – |
| OpenAI | 44 tok/s | 2.56 s | $4.00 | $20.00 | 1.1M | – |
| Azure | 43 tok/s | 4.92 s | $2.00 | $10.00 | 1.1M | – |
| OpenAI | 40 tok/s | 2.77 s | $2.00 | $10.00 | 1.1M | – |
| Azure | 37 tok/s | 3.71 s | $2.20 | $11.00 | 1.1M | – |
| OpenAI | 27 tok/s | 9.96 s | $1.00 | $5.00 | 1.1M | – |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.100 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0038 | $0.0032 | 5.5 min |
| Summarise a 30-page report | 12,000 / 600 | $0.030 | $0.013 | 5.6 min |
| Code edit | 6,000 / 1,500 | $0.027 | $0.018 | 5.9 min |
| Agentic coding session | 60,000 / 4,000 | $0.160 | $0.074 | 6.7 min |
| Structured extraction | 2,000 / 200 | $0.0060 | $0.0032 | 5.5 min |
See also
Data as of 11 Oct 2026. Compare these configurations.
Cite as: BenchLeader, “GPT-6.1 Sol: benchmarks, pricing, speed and rank”, https://www.benchleader.com/models/gpt-6-1-sol, data as of 11 Oct 2026.