GPT-5.5 Pro vs GPT-5.6 Sol
Full profiles: GPT-5.5 Pro (OpenAI) and GPT-5.6 Sol (OpenAI): every benchmark, price and rank.
Updated · Data from 10 sources
As of 16 Nov 2026, there are not enough shared benchmarks for a verdict, and GPT-5.6 Sol is 8.4× cheaper at $8.00 vs $67.50 per 1M tokens blended. GPT-5.5 Pro leads in every category we measure both in. GPT-5.6 Sol streams 3×+ faster.
Key facts (as of 16 Nov 2026)
- GPT-5.5 Pro costs $67.50 per 1M tokens blended (list price, 16 Nov 2026).
- GPT-5.6 Sol costs $8.00 per 1M tokens blended (list price, 16 Nov 2026).
- GPT-5.6 Sol streams 3×+ faster than GPT-5.5 Pro (Artificial Analysis, 7-day median, 16 Nov 2026).
- Of the 8 benchmarks both models have, GPT-5.6 Sol leads 6 (BenchLeader, 16 Nov 2026).
Which to pick for…
The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.
| Use case | Pick | Why | Confidence |
|---|---|---|---|
| Maths | Either | 70 vs 70 category score; FrontierMath Tiers 1–3 87.7% vs 89.1% | Either |
| Reasoning | GPT-5.5 Pro | 68 vs 65 category score; ARC-AGI-2 84.2% vs 92.5% | Medium |
| Lowest cost | GPT-5.6 Sol | $8.00 vs $67.50 per 1M blended; agentic coding session $0.320 vs $2.52 | – |
| Fastest first answer | GPT-5.5 Pro | 6.0 s (GPT-5.5 Pro (xhigh)) vs 33.5 s (GPT-5.6 Sol (max)) to the first answer token | – |
| High volume on a budget | Neither flagship | A smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs | – |
Key differences
- Not enough shared benchmarks for a verdict.
- GPT-5.5 Pro (xhigh) is stronger in reasoning.
- GPT-5.6 Sol (max) is 8.4× cheaper ($8.00 vs $67.50 per 1M blended).
- GPT-5.6 Sol (max) streams 4.8× faster (100 vs 21 tokens per second).
At a glance
| Spec | GPT-5.5 Pro | GPT-5.6 Sol |
|---|---|---|
| Developer | OpenAI | OpenAI |
| Released | 23 Apr 2026 | 9 Jul 2026 |
| Context window (tokens) | 1,050,000 | 1,050,000 |
| Compared at | GPT-5.5 Pro (xhigh) | GPT-5.6 Sol (max) |
| Open weights | No | No |
| Price in / out / cached input per 1M | $30.00 / $180.00 / – | $4.00 / $20.00 / $0.400 |
Category by category
Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.
| Category | GPT-5.5 Pro (xhigh) | GPT-5.6 Sol (max) | Leader |
|---|---|---|---|
| Reasoning | 67.9 | 64.7 | GPT-5.5 Pro |
| Coding | – | 65.8 | not comparable |
| Agents & tools | – | 67.5 | not comparable |
| Maths | 70.0 | 70.0 | level |
| Knowledge | – | 63.8 | not comparable |
| Instruction following | – | 71.2 | not comparable |
| Multimodal | – | 65.9 | not comparable |
| Long context | – | 66.7 | not comparable |
On one chart
Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.
Dashed: that model has no result on the axis it crosses; the line only joins its neighbours.
Not drawn, no result for these models: Human preference.
Where sources disagree
Across the 8 benchmarks both have, GPT-5.5 Pro leads 2, GPT-5.6 Sol leads 6.
Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).
Price, speed and latency
List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.
| Measure | GPT-5.5 Pro (xhigh) | GPT-5.6 Sol (max) |
|---|---|---|
| Blended price per 1M tokens | $67.50 | $8.00 |
| Input / output per 1M | $30.00 / $180.00 | $4.00 / $20.00 |
| Cached input per 1M | – | $0.400 |
| Price per task: chat reply | $0.066 | $0.0076 |
| Price per task: summarize a 30-page report | $0.468 | $0.060 |
| Price per task: code edit | $0.450 | $0.054 |
| Price per task: agentic coding session | $2.52 | $0.320 |
| Price per task: structured extraction | $0.096 | $0.012 |
| Agentic coding session, input mostly cached | – | $0.158 |
| Output speed | 21 tok/s | 100 tok/s |
| Time to first answer | 6.0 s | 33.5 s |
| Time to a complete answer, last measured 13 Nov 2026 | – | 157.3 s |
Each model is compared at its best-ranked reasoning-effort setting. GPT-5.5 Pro (xhigh) and takes 6 s to its first answer token. GPT-5.6 Sol (max) scores 65.3 and takes 34 s to its first answer token; GPT-5.6 Sol (xhigh) scores 63.9 in 17 s, GPT-5.6 Sol (high) scores 63.4 in 10 s. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.
Every benchmark
150 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.
| Metric | Publisher | GPT-5.5 Pro (xhigh) | GPT-5.6 Sol (max) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | – | 65.3 |
| Maths score | BenchLeader | 70.0 | 70.0 |
| Reasoning score | BenchLeader | 67.9 | 64.7 |
| Agents & tools score | BenchLeader | – | 67.5 |
| Coding score | BenchLeader | – | 65.8 |
| Instruction following score | BenchLeader | – | 71.2 |
| Knowledge score | BenchLeader | – | 63.8 |
| Long context score | BenchLeader | – | 66.7 |
| Multimodal score | BenchLeader | – | 65.9 |
| Blended price $/M | BenchLeader | $67.50 | $8.00 |
| Output speed | BenchLeader | 21 tok/s | 100 tok/s |
| Time to first answer | BenchLeader | 6.0 s | 33.5 s |
| Context window | BenchLeader | 1,050,000 tokens | 1,050,000 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | – | 93.5% |
| SimpleBench | SimpleBench | 76.9%† | 64.8%† |
| Arena Hard Prompts | Arena (LMArena) | – | 1511† |
| LiveBench 1.0 Reasoning | LiveBench | – | 91.7% |
| GPQA Diamond (AA) | Artificial Analysis | – | 94.1% |
| Humanity's Last Exam (AA) | Artificial Analysis | – | 49.5% |
| GPQA Diamond (Vals) | Vals AI | – | 95.2% |
| EnigmaEval | Scale AI SEAL | – | 37.1%† |
| Kagi LLM Benchmark | Kagi LLM Benchmark | – | 67.0%† |
| ARC-AGI-1 | ARC Prize | 95.0% | 96.5% |
| ARC-AGI-2 | ARC Prize | 84.2% | 92.5% |
| ARC-AGI-3 | ARC Prize | – | 7.8% |
| CritPt | Artificial Analysis | 30.6% | 32.3% |
| CritPt v2 hard subset (AA) | Artificial Analysis | – | 60.0% |
| MysteryMechanism | Vals AI | – | 33.3% |
| HLE-Diamond (Scale) | Scale AI SEAL | – | 31.2%† |
| Arena Expert | Arena (LMArena) | – | 1532† |
| Chess Puzzles | Epoch AI Benchmarking Hub | 62.0% | 59.0% |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | – | 58.0% |
| LMCA | Epoch AI Benchmarking Hub | 53.9% | 58.4% |
| DTBench | Epoch AI Benchmarking Hub | 96.0% | 95.5% |
| ForecastBench | ForecastBench | – | 65.7% |
| BTF-3 | Epoch AI Benchmarking Hub | – | 13.7% |
| Coding | |||
| SciCode | SciCode | – | 57.1% |
| WeirdML | WeirdML | – | 87.0% |
Show all 150 benchmarks
| Metric | Publisher | GPT-5.5 Pro (xhigh) | GPT-5.6 Sol (max) |
|---|---|---|---|
| Coding | |||
| FrontierCode | Cognition | – | 47.5%† |
| GSO-Bench | GSO-Bench | – | 76.5%† |
| Arena Coding | Arena (LMArena) | – | 1533† |
| Arena WebDev | Arena (LMArena) | – | 1615† |
| LiveBench 1.0 Coding | LiveBench | – | 83.9% |
| LiveCodeBench | Vals AI | – | 82.6% |
| IOI | Vals AI | – | 91.2% |
| SWE-bench (Vals) | Vals AI | – | 96.2% |
| Code Migration | Vals AI | – | 52.9% |
| ProgramBench | Vals AI | – | 1.5% |
| Vibe Code Bench 1-100 | Vals AI | – | 20.0% |
| Vibe Code Bench v1.1 | Vals AI | – | 80.5% |
| SWE Atlas v1.0: Codebase QnA | Scale AI SEAL | – | 46.0%† |
| SWE Atlas v1.0: Test Writing | Scale AI SEAL | – | 45.9%† |
| SWE-Bench Pro V2 | Scale AI SEAL | – | 95.5%† |
| SWE-Bench Pro V2 HARD | Scale AI SEAL | – | 82.4%† |
| MirrorCode | Epoch AI Benchmarking Hub | – | 20.0%† |
| Surface Evolver Bench | Epoch AI Benchmarking Hub | – | 93.1%† |
| DeepSWE v1.1 | Epoch AI Benchmarking Hub | – | 72.7% |
| CursorBench | Cursor | – | 41.7% |
| ALE-Bench | Epoch AI Benchmarking Hub | – | 2176.9 |
| FrontierSWE | Epoch AI Benchmarking Hub | – | 32.2% |
| WeirdML v3 | WeirdML | – | 15.0%† |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | – | 39.9% |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | – | 88.0% |
| Startrise Frontend | Startrise | – | 66.2%† |
| GameBench 2 Overall | DuelLab GameBench 2 | – | 67.0† |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | – | 80.0† |
| Design Arena Website | Design Arena | – | 1319† |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | – | 38.5% |
| OSWorld-Verified 2.0 | OSWorld | – | 27.3% |
| APEX-Agents | Mercor | – | 51.4%† |
| Arena Agent | Arena (LMArena) | – | 4.6† |
| LiveBench Agentic Coding | LiveBench | – | 56.2% |
| Terminal-Bench Hard | Artificial Analysis | – | 65.9% |
| τ²-Bench Telecom (AA) | Artificial Analysis | – | 85.1% |
| Terminal-Bench 2.1 (Vals) | Vals AI | – | 85.8% |
| HiL-Bench | Scale AI SEAL | – | 32.3%† |
| τ³-bench Banking | τ²-bench | – | 46.9%† |
| GDPval-AA v2.1 | Artificial Analysis | – | 1619 |
| τ³-Banking (AA) | Artificial Analysis | – | 44.3% |
| ITBench SRE (AA) | Artificial Analysis | – | 56.2% |
| Analyst Agent (AA) | Artificial Analysis | – | 47.5% |
| CUA-bench | Vals AI | – | 8.3% |
| CyberBench | Vals AI | – | 76.3% |
| Finance Agent v2 | Vals AI | – | 53.8% |
| Harvey's Legal Agent Benchmark v1 | Vals AI | – | 2.5% |
| Legal Research Bench | Vals AI | – | 48.1% |
| SkillsBench | Vals AI | – | 54.1% |
| SREBench | Vals AI | – | 30.5% |
| Tax Agent Bench | Vals AI | – | 31.1% |
| Terminal-Bench 4.0 (Vals) | Vals AI | – | 37.9% |
| Terminal-Bench Science | Vals AI | – | 20.0% |
| Time Horizon Index: KSP | Vals AI | – | 23.8% |
| Web Search Index | Vals AI | – | 43.6% |
| Arena Search | Arena (LMArena) | – | 1255† |
| Arena Agent Task Completion | Arena (LMArena) | – | 2.3† |
| BALROG | BALROG | – | 60.0% |
| PostTrainBench | Epoch AI Benchmarking Hub | – | 31.0% |
| GBAEval | Epoch AI Benchmarking Hub | – | 52.6%† |
| Vending-Bench 2 | Andon Labs | – | 9619.4† |
| AutomationBench | Artificial Analysis | – | 60.1% |
| GDP.pdf (AA) | Artificial Analysis | – | 27.2% |
| EnterpriseOps-Gym | Artificial Analysis | – | 42.9% |
| AA-Briefcase v1.1 | Artificial Analysis | – | 1479 |
| Design Arena Agentic | Design Arena | – | 1238† |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | – | 22.4% |
| FACTS Search | – | 92.9%† | |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 87.7% | 89.1% |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 78.0% | 82.9% |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | – | 100.0% |
| ProofBench | Vals AI | – | 83.0% |
| LiveBench Mathematics | LiveBench | – | 96.2% |
| Arena Maths | Arena (LMArena) | – | 1494† |
| FrontierMath Erdős | Epoch AI Benchmarking Hub | – | 0.0% |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | – | 69.7% |
| LiveBench 1.0 Data Analysis | LiveBench | – | 79.8% |
| MMLU-Pro | Vals AI | – | 89.1% |
| LegalBench | Vals AI | – | 87.0% |
| CorpFin | Vals AI | – | 64.4% |
| TaxEval | Vals AI | – | 74.8% |
| PRBench Finance | Scale AI SEAL | – | 50.5% |
| PRBench Legal | Scale AI SEAL | – | 50.5% |
| BioMysteryBench | Vals AI | – | 71.1% |
| Excel Modeling Benchmark | Vals AI | – | 72.3% |
| MedCode | Vals AI | – | 44.0% |
| MedScribe | Vals AI | – | 85.2% |
| Public Benefits Bench v1.1 | Vals AI | – | 66.5% |
| Financial Coaching Bench | Vals AI | – | 74.9% |
| DrugDiscoveryBench | Scale AI SEAL | – | 56.5% |
| EBR-bench | Epoch AI Benchmarking Hub | – | 44.8% |
| GDP.pdf | Epoch AI Benchmarking Hub | – | 30.7% |
| FACTS Parametric | – | 81.1%† | |
| Instruction following | |||
| LiveBench Language | LiveBench | – | 87.7% |
| LiveBench Instruction Following | LiveBench | – | 71.8% |
| IFBench | Artificial Analysis | – | 72.7% |
| Arena Instruction Following | Arena (LMArena) | – | 1490† |
| Human preference | |||
| Arena Text | Arena (LMArena) | – | 1485† |
| EQ-Bench 4 | EQ-Bench | – | 1236† |
| EQ-Bench Creative Writing v3 | EQ-Bench | – | 1974† |
| Arena Creative Writing | Arena (LMArena) | – | 1471† |
| Arena Multi-turn | Arena (LMArena) | – | 1491† |
| Arena Longer Queries | Arena (LMArena) | – | 1498† |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | – | 1282† |
| MMMU-Pro | Artificial Analysis | – | 83.4% |
| MMMU-Pro (Vals) | Vals AI | – | 88.8% |
| MortgageTax | Vals AI | – | 67.3% |
| Humanity's Sixth Sense | Scale AI SEAL | – | 30.0% |
| GeoBench | GeoBench | – | 73.0%† |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | – | 33.6%† |
| Furniture Assembly | Epoch AI Benchmarking Hub | – | 56.7% |
| FACTS Multimodal | – | 46.4%† | |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | – | 84.0% |
| Arena Document | Arena (LMArena) | – | 1487† |
| MLCR | Artificial Analysis | – | 30.0% |
| FACTS Grounding | – | 61.9%† | |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 162.7† | 163.0† |
| LiveBench 1.0 | LiveBench | – | 81.0% |
| AA Intelligence Index v4.3.2 | Artificial Analysis | – | 47.0 |
| AA Progress Index v1 | Artificial Analysis | – | 331.5 |
| Vals RSI Index | Vals AI | – | 23.9% |
| Vals Science Index | Vals AI | – | 41.5% |
| Vals Multimodal Index | Vals AI | – | 72.6% |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | – | 20.1%† |
| DistressBench | Scale AI SEAL | – | 73.6%† |
Data as of 2026-11-16. Best configuration of each model; every score links to its source on the model pages.
DuelLab GameBench 2, release gb2-20261111-7b598bb13de4 (https://benchmarks.duellab.org/releases/gb2-20261111-7b598bb13de4/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.
What changed
- GPT-5.6 Sol (max): 1 new result (GDPval-AA v2.1).
- GPT-5.6 Sol (max): 1 score revision.
- GPT-5.6 Sol (max): BenchLeader Index 65.8 → 65.3.
- GPT-5.6 Sol (max): 1 score revision.
- GPT-5.6 Sol (max): 1 score revision.
- GPT-5.6 Sol (max): 2 new results (AA Progress Index v1, CritPt v2 hard subset (AA)).
- GPT-5.6 Sol (max): 1 new result (AA-Briefcase v1.1).
- GPT-5.6 Sol (max): 3 new results (Harvey's Legal Agent Benchmark v1, Vals RSI Index, Vals Science Index).
- GPT-5.6 Sol (max): 1 score revision.
- GPT-5.6 Sol (max): 1 new result (ForecastBench).
Related comparisons
- GPT-5.5 Pro vs Gemini 4 Argon
- GPT-5.6 Sol vs Claude Fable 5.2
- GPT-5.6 Sol vs Gemini 4 Carbon
- GPT-5.6 Sol vs Claude Opus 5.5
- GPT-5.6 Sol vs GPT-6 Astra
- GPT-5.4 vs GPT-5.6 Sol
- GPT-5.5 Pro vs GPT-6 Sol
- GPT-5.5 Pro vs Gemini 3 Pro
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
GPT-5.5 Pro vs GPT-5.6 Sol: questions
- GPT-5.5 Pro vs GPT-5.6 Sol: which is cheaper, and will that change?
- GPT-5.6 Sol is cheaper today: $8.00 against $67.50 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Which is faster, GPT-5.5 Pro or GPT-5.6 Sol?
- GPT-5.6 Sol streams 3×+ faster (100 vs 21 output tokens per second, Artificial Analysis 7-day median).
- Which is better for long documents?
- Both accept 1,050,000 tokens of context.
- Which has lower latency?
- GPT-5.5 Pro answers first: 6.0 s against 33.5 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
- Do independent benchmarks agree on GPT-5.5 Pro vs GPT-5.6 Sol?
- Across the 8 benchmarks both have, GPT-5.5 Pro leads 2, GPT-5.6 Sol leads 6.
More questions (1)
- When was GPT-5.6 Sol released?
- GPT-5.6 Sol was released on 9 Jul 2026.