OpenAIGPT-6 Sol
GPT-6 Sol is an OpenAI proprietary reasoning model, released 22 Sept 2026. Its best configuration (max reasoning effort) ranks #30 of 775 on the BenchLeader Index at 66.6 ±3.9, in the upper half. The ± is the point: 94 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 (83) and lowest in agents & tools (60). At $4.00 per million tokens blended it is among the most expensive ranked models. Output speed of 118 tokens per second puts it faster than most, with a first answer in 89.9 s. It has been measured at 7 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 19 Oct 2026.
- Blended price
- $4.00/M
- $2.00 in · $10.00 out
- Output speed
- 118 tok/s
- measured by Artificial Analysis
- First answer
- 90 s
- first token 2.12 s
- Context
- 1.1M
- Full answer
- 94 s
- median, reasoning included
- Cost per run
- $1.04
- one full Intelligence Index run
- Released
- 22 Sept 2026
- Overall index67
- Reasoning72
- Coding67
- Agents & tools60
- Maths69
- Knowledge70
- Human preference65
- Multimodal62
- Long context67
- Composite83
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 Solmax | 29 Sept 2026 | 70.0 | #7 |
| GPT-6 Solmaxthis page | 22 Sept 2026 | 66.6 | #30 |
| GPT-5.6 Solmax | 9 Jul 2026 | 68.0 | #16 |
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 |
|---|---|---|---|---|---|---|
| no reasoning | 52.8 | #299 | 107 tok/s | 0.81 s | $0.0038 | Coding 50 · Composite 62 · Knowledge 61 · Long context 57 · Multimodal 53 · Reasoning 40 |
| low | 59.7 | #125 | 101 tok/s | 1.44 s | $0.0038 | Coding 54 · Composite 68 · Knowledge 73 · Long context 65 · Multimodal 63 · Reasoning 54 |
| medium | 62.6 | #83 | 63 tok/s | 2.12 s | $0.0038 | Coding 59 · Composite 74 · Knowledge 74 · Long context 66 · Multimodal 64 · Reasoning 64 |
| high | 63.8 | #58 | 109 tok/s | 16 s | $0.0038 | Coding 61 · Composite 77 · Knowledge 74 · Long context 67 · Multimodal 65 · Reasoning 67 |
| xhigh | 64.4 | #53 | 108 tok/s | 57 s | $0.0038 | Coding 61 · Composite 79 · Knowledge 74 · Long context 66 · Multimodal 66 · Reasoning 70 |
| maxbest | 66.6 | #30 | 118 tok/s | 90 s | $0.0038 | Agents & tools 60 · Coding 67 · Composite 83 · Human preference 65 · Knowledge 70 · Long context 67 · Maths 69 · Multimodal 62 · Reasoning 72 |
| not stated | – | – | 63 tok/s | 2.12 s | $0.0038 | Composite 66 · Knowledge 37 · Maths 70 |
What more thinking costs
Turning the effort up buys index points and multiplies the bill. Here max costs 7.9× low for +6.9 on the index — 2.3 points per doubling of spend. Compare that with other models.
How its index has moved
23 Sept 2026 to 19 Oct 2026- max
- xhigh
- high
- medium
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
See all LLM benchmarks. 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 | no reasoning | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|---|
| GPQA Diamond | – | – | – | – | – | 94.3%#9 | – | Epoch AI Benchmarking Hub | |
| Arena Hard Prompts | – | – | – | – | – | 1484#58 | – | Arena (LMArena) | |
| LiveBench 2.0 Reasoningnot in indexeffort not stated | – | – | – | – | – | – | 88.7%#20 | LiveBench | |
| LiveBench 1.0 Reasoningnot in index | – | – | – | – | – | 88.7%#22 | – | LiveBench | |
| Humanity's Last Exam (AA)not in index | 18.4%#227 | 34.9%#121 | 41.0%#80 | 44.1%#52 | 46.3%#44 | 47.9%#35 | – | Artificial Analysis | |
| ARC-AGI-1 | 29.3%#196 | 72.2%#131 | 83.7%#108 | 91.0%#63 | 92.7%#49 | 95.5%#31 | – | ARC Prize | |
| ARC-AGI-2 | 1.7%#197 | 31.5%#121 | 57.8%#91 | 68.9%#58 | 78.1%#41 | 89.6%#17 | – | ARC Prize | |
| ARC-AGI-3 | 1.2%#36 | 1.8%#34 | 4.9%#27 | 5.9%#26 | 9.5%#21 | 23.0%#18 | – | ARC Prize | |
| CritPt | 4.0%#165 | 16.3%#86 | 24.6%#46 | 25.4%#42 | 28.0%#28 | 30.9%#12 | – | Artificial Analysis | |
| MysteryMechanismnot in index | – | – | – | – | – | 30.2%#14 | – | Vals AI | |
| Chess Puzzlesnot in index | – | – | – | – | – | 56.0%#15 | – | Epoch AI Benchmarking Hub | |
| Mystery Game Puzzlesnot in index | – | – | – | – | – | 56.0%#9 | – | Epoch AI Benchmarking Hub | |
| LMCAnot in index | – | – | – | – | – | 59.1%#36 | – | Epoch AI Benchmarking Hub | |
| DTBenchnot in index | – | – | – | – | – | 97.3%#9 | – | Epoch AI Benchmarking Hub |
Coding
| Benchmark | no reasoning | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|---|
| SciCode | 47.3%#124 | 50.2%#106 | 53.8%#70 | 54.9%#57 | 55.1%#50 | 57.6%#26 | – | SciCode | |
| FrontierCode | – | – | – | – | – | 49.3%#9 | – | Cognition | |
| Arena Coding | – | – | – | – | – | 1518#39 | – | Arena (LMArena) | |
| Arena WebDev | – | – | – | – | – | 1683#9 | – | Arena (LMArena) | |
| LiveBench 2.0 Codingnot in indexeffort not stated | – | – | – | – | – | – | 93.1%#9 | LiveBench | |
| LiveBench 1.0 Codingnot in index | – | – | – | – | – | 81.8%#13 | – | LiveBench | |
| SciCode (AA)not in index | 47.3%#131 | 50.2%#107 | 53.8%#73 | 54.9%#58 | 55.1%#52 | 57.6%#26 | – | Artificial Analysis | |
| IOI | – | – | – | – | – | 82.6%#10 | – | Vals AI | |
| Code Migrationnot in index | – | – | – | – | – | 57.2%#9 | – | Vals AI | |
| ProgramBenchnot in index | – | – | – | – | – | 2.0%#10 | – | Vals AI | |
| Vibe Code Bench v1.1not in index | – | – | – | – | – | 87.8%#10 | – | Vals AI | |
| ALE-Benchnot in index | – | – | – | – | – | 2462#3 | – | Epoch AI Benchmarking Hub | |
| Terminal-Bench 4.0 (AA)not in index | 13.1%#75 | 9.1%#89 | 18.7%#65 | 26.3%#50 | 30.3%#45 | 43.9%#25 | – | Artificial Analysis |
Agents & tools
| Benchmark | no reasoning | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|---|
| Terminal-Bench | – | – | – | – | – | 49.4%#36 | – | Terminal-Bench | |
| APEX-Agents | – | – | – | – | – | 54.3%#23 | – | Mercor | |
| Arena Agent | – | – | – | – | – | 9.3#7 | – | Arena (LMArena) | |
| LiveBench Long Agenticnot in indexeffort not stated | – | – | – | – | – | – | 66.9%#7 | LiveBench | |
| LiveBench Browsernot in indexeffort not stated | – | – | – | – | – | – | 92.0%#3 | LiveBench | |
| LiveBench Agentic Codingnot in index | – | – | – | – | – | 52.9%#37 | – | LiveBench | |
| Terminal-Bench 2.1 (Vals) | – | – | – | – | – | 83.2%#6 | – | Vals AI | |
| GDPval-AA v2.1not in index | 37.5%#109 | 35.0%#120 | 42.3%#90 | 44.7%#76 | 47.8%#59 | 50.4%#50 | – | Artificial Analysis | |
| ITBench SRE (AA)not in index | – | – | – | – | – | 49.4%#7 | – | Artificial Analysis | |
| CyberBenchnot in index | – | – | – | – | – | 78.0%#2 | – | Vals AI | |
| Finance Agent v2not in index | – | – | – | – | – | 49.0%#47 | – | Vals AI | |
| Legal Research Benchnot in index | – | – | – | – | – | 28.9%#50 | – | Vals AI | |
| SREBenchnot in index | – | – | – | – | – | 30.5%#6 | – | Vals AI | |
| Tax Agent Benchnot in index | – | – | – | – | – | 15.0%#51 | – | Vals AI | |
| Terminal-Bench 4.0 (Vals)not in index | – | – | – | – | – | 44.4%#10 | – | Vals AI | |
| Terminal-Bench Sciencenot in index | – | – | – | – | – | 30.0%#8 | – | Vals AI | |
| Arena Searchnot in index | – | – | – | – | – | 1228#7 | – | Arena (LMArena) | |
| Vending-Bench 2not in indexeffort not stated | – | – | – | – | – | – | 14427.9#2 | Andon Labs | |
| AutomationBenchnot in index | 34.2%#110 | 53.9%#63 | 58.0%#44 | 60.1%#34 | 61.7%#29 | 61.6%#30 | – | Artificial Analysis | |
| GDP.pdf (AA)not in index | 17.0%#86 | 24.2%#35 | 23.8%#40 | 24.4%#34 | 24.6%#31 | 25.2%#29 | – | Artificial Analysis | |
| Harvey LAB-AA v1.1not in index | – | – | – | – | – | 3.6%#11 | – | Harvey | |
| AA-Briefcase v1.1not in index | – | – | – | – | – | 1481#33 | – | Artificial Analysis | |
| Terminal-Bench-Science 0.1 (AA)not in index | 5.7%#35 | 3.3%#42 | 8.6%#31 | 17.1%#19 | 17.6%#18 | 30.0%#12 | – | Artificial Analysis | |
| CWE-Bench (AA) | – | – | – | – | – | 64.2%#3 | – | Artificial Analysis | |
| DeepSec-Bench (AA) | – | – | – | – | – | 46.3%#1 | – | Artificial Analysis | |
| CyberGym end-to-end (AA) | – | – | – | – | – | 0.0%#16 | – | Artificial Analysis | |
| FACTS Searchnot in indexeffort not stated | – | – | – | – | – | – | 86.2%#5 |
Maths
| Benchmark | max | not stated | Source | Trend |
|---|---|---|---|---|
| FrontierMath Tiers 1–3 | 89.8%#5 | – | Epoch AI Benchmarking Hub | |
| FrontierMath Tier 4 | 90.0%#8 | – | Epoch AI Benchmarking Hub | |
| OTIS Mock AIME | 100.0%#1 | – | Epoch AI Benchmarking Hub | |
| ProofBencheffort not stated | – | 83.0%#12 | Vals AI | |
| LiveBench Mathematicsnot in index | 96.4%#9 | – | LiveBench | |
| Arena Maths | 1450#75 | – | Arena (LMArena) |
Knowledge
| Benchmark | no reasoning | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|---|
| SimpleQA Verified | – | – | – | – | – | 60.7%#15 | – | Epoch AI Benchmarking Hub | |
| LiveBench 2.0 Data Analysisnot in indexeffort not stated | – | – | – | – | – | – | 81.2%#6 | LiveBench | |
| LiveBench Researchnot in indexeffort not stated | – | – | – | – | – | – | 69.3%#31 | LiveBench | |
| LiveBench 1.0 Data Analysisnot in index | – | – | – | – | – | 81.2%#6 | – | LiveBench | |
| AA-Omniscience | -0.8#142 | 26.5#47 | 27.0#44 | 26.8#45 | 26.7#46 | 27.1#43 | – | Artificial Analysis | |
| PRBench Legaleffort not stated | – | – | – | – | – | – | 38.6%#34 | Scale AI SEAL | |
| BioMysteryBenchnot in index | – | – | – | – | – | 74.8%#7 | – | Vals AI | |
| Excel Modeling Benchmarknot in index | – | – | – | – | – | 71.5%#11 | – | Vals AI | |
| MedCodenot in index | – | – | – | – | – | 47.1%#36 | – | Vals AI | |
| MedScribenot in index | – | – | – | – | – | 82.0%#50 | – | Vals AI | |
| Public Benefits Benchnot in index | – | – | – | – | – | 56.6%#37 | – | Vals AI | |
| EBR-benchnot in index | – | – | – | – | – | 53.3%#6 | – | Epoch AI Benchmarking Hub | |
| GDP.pdfnot in index | – | – | – | – | – | 26.4%#15 | – | Epoch AI Benchmarking Hub | |
| AA-Omniscience: accuracynot in index | 45.2%#90 | 51.3%#58 | 53.5%#47 | 53.7%#45 | 53.9%#44 | 54.5%#41 | – | Artificial Analysis | |
| AA-Omniscience: non-hallucinationnot in index | 16.0%#329 | 49.3%#118 | 43.2%#147 | 41.9%#151 | 41.1%#154 | 39.9%#159 | – | Artificial Analysis |
Instruction following
| Benchmark | max | Source | Trend |
|---|---|---|---|
| LiveBench Languagenot in index | 85.3%#15 | LiveBench | |
| LiveBench Instruction Followingnot in index | 68.6%#34 | LiveBench | |
| Arena Instruction Followingnot in index | 1452#62 | Arena (LMArena) |
Human preference
| Benchmark | max | Source | Trend |
|---|---|---|---|
| Arena Text | 1459#61 | Arena (LMArena) | |
| Arena Creative Writingnot in index | 1438#60 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1467#66 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1465#69 | Arena (LMArena) |
Multimodal
| Benchmark | no reasoning | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|---|
| Arena Vision | – | – | – | – | – | 1240#73 | – | Arena (LMArena) | |
| LiveBench Designnot in indexeffort not stated | – | – | – | – | – | – | 82.2%#9 | LiveBench | |
| MMMU-Pro | 70.3%#143 | 80.2%#50 | 80.4%#48 | 82.0%#35 | 82.5%#31 | 83.0%#28 | – | Artificial Analysis | |
| SAGEnot in index | – | – | – | – | – | 44.8%#44 | – | Vals AI | |
| Blueprint-Bench 2not in indexeffort not stated | – | – | – | – | – | – | 36.9%#8 | Epoch AI Benchmarking Hub | |
| AA-3Dnot in index | – | – | – | – | – | 1123#6 | – | Artificial Analysis |
Long context
| Benchmark | no reasoning | low | medium | high | xhigh | max | Source | Trend |
|---|---|---|---|---|---|---|---|---|
| AA-LCR | 64.0%#257 | 79.3%#97 | 82.3%#40 | 83.7%#15 | 81.3%#55 | 83.7%#15 | Artificial Analysis | |
| MLCRnot in index | – | – | – | – | – | 16.1%#41 | Artificial Analysis |
Composite
| Benchmark | no reasoning | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|---|
| Epoch Capabilities Indexnot in indexeffort not stated | – | – | – | – | – | – | 163.7#8 | Epoch AI Benchmarking Hub | |
| LiveBench 2.0effort not stated | – | – | – | – | – | – | 81.9%#9 | LiveBench | |
| LiveBench 1.0not in index | – | – | – | – | – | 79.3%#14 | – | LiveBench | |
| AA Intelligence Index v4.3.2 | 28.5#131 | 34.1#97 | 39.8#64 | 42.4#49 | 44.2#41 | 47.6#27 | – | Artificial Analysis | |
| AA Cyber Indexnot in index | – | – | – | – | – | 36.8#9 | – | Artificial Analysis |
Safety & honesty
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| FORTRESSnot in index | 13.5%#58 | Scale AI SEAL |
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 |
|---|---|---|---|---|---|---|
| Azure | 118 tok/s | 7.77 s | $2.20 | $11.00 | 1.1M | – |
| OpenAI | 89 tok/s | 1.74 s | $4.00 | $20.00 | 1.1M | – |
| Amazon Bedrock | 65 tok/s | 3.57 s | $2.20 | $11.00 | 1.1M | – |
| OpenAI | 63 tok/s | 2.12 s | $2.00 | $10.00 | 1.1M | – |
| OpenAI | 59 tok/s | 1.21 s | $1.00 | $5.00 | 1.1M | – |
| Azure | 39 tok/s | 3.17 s | $2.00 | $10.00 | 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 $0.200 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0038 | $0.0033 | 1.5 min |
| Summarize a 30-page report | 12,000 / 600 | $0.030 | $0.014 | 1.6 min |
| Code edit | 6,000 / 1,500 | $0.027 | $0.019 | 1.7 min |
| Agentic coding session | 60,000 / 4,000 | $0.160 | $0.079 | 2.1 min |
| Structured extraction | 2,000 / 200 | $0.0060 | $0.0033 | 1.5 min |
More from OpenAI
Compare GPT-6 Sol with…
- GPT-6 Sol vs Claude Opus 5.5
- GPT-6 Sol vs Gemini 4 Argon
- GPT-6 Sol vs Muse Wonder Full
- GPT-6 Sol vs GPT-6 Astra
- GPT-6 Sol vs Claude Fable 5.1
- GPT-6 Sol vs GPT-6.1 Sol
- GPT-6 Sol vs Claude Sonnet 5.5
- GPT-6 Sol vs Claude Fable 5
- GPT-6 Sol vs Claude Opus 5
- GPT-6 Sol vs GPT-5.6 Sol
- GPT-6 Sol vs Muse Wonder
- GPT-6 Sol vs Muse Spark 1.3
- GPT-6 Sol vs GPT-5.5
- GPT-6 Sol vs GPT-5.5 Pro
- GPT-6 Sol vs Kimi K3
- GPT-6 Sol vs GPT-5.4
- GPT-6 Sol vs Gemini 3.8 Flash
- GPT-6 Sol vs Muse Spark
- GPT-6 Sol vs GPT-5.6 Terra
- GPT-6 Sol vs MiMo-V2.6-Pro
- GPT-6 Sol vs Grok 4.6
- GPT-6 Sol vs Grok 4.7
- GPT-6 Sol vs GPT-5.3-Codex
- GPT-6 Sol vs GLM 5.3
- GPT-6 Sol vs Gemini 3.7 Flash
- GPT-6 Sol vs GPT-5.4 Pro
- GPT-6 Sol vs Claude Opus 4.7
- GPT-6 Sol vs Claude Opus 4.8
- GPT-6 Sol vs Qwen3.8 Max
- GPT-6 Sol vs Gemini 3.5 Flash
- GPT-6 Sol vs Muse Spark 1.2
- GPT-6 Sol vs Qwen3.8 2.4T A95B
- GPT-6 Sol vs DeepSeek V4.1 Flash 1017
- GPT-6 Sol vs Muse Spark 1.1
- GPT-6 Sol vs Claude Opus 4.6
- GPT-6 Sol vs GLM 5.3 Flash
- GPT-6 Sol vs DeepSeek V4 Pro
- GPT-6 Sol vs GLM 5.2
- GPT-6 Sol vs Qwen3.6 Max
See also
Data as of 21 Oct 2026. Compare these configurations.
Cite as: BenchLeader, “GPT-6 Sol: benchmarks, pricing, speed and rank”, https://www.benchleader.com/models/gpt-6-sol, data as of 21 Oct 2026.