GPT-5.4 Pro vs GPT-6 Sol
Full profiles: GPT-5.4 Pro (OpenAI) and GPT-6 Sol (OpenAI): every benchmark, price and rank.
Updated · Data from 11 sources
As of 9 Nov 2026, GPT-5.4 Pro and GPT-6 Sol are neck and neck on quality (63.3 vs 62.9 on the BenchLeader Index, inside the ±4.9 margin), and GPT-6 Sol is 17× cheaper at $4.00 vs $67.50 per 1M tokens blended. GPT-5.4 Pro leads in every category we measure both in. GPT-6 Sol streams 3×+ faster.
Key facts (as of 9 Nov 2026)
- GPT-5.4 Pro scores 63.3 on the BenchLeader Index and GPT-6 Sol scores 62.9 (BenchLeader, 9 Nov 2026).
- GPT-5.4 Pro costs $67.50 per 1M tokens blended (list price, 9 Nov 2026).
- GPT-6 Sol costs $4.00 per 1M tokens blended (list price, 9 Nov 2026).
- GPT-6 Sol streams 3×+ faster than GPT-5.4 Pro (Artificial Analysis, 7-day median, 9 Nov 2026).
GPT-5.4 Pro benchmarks 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 |
|---|---|---|---|
| Reasoning | GPT-5.4 Pro | 73 vs 66 category score | Medium |
| Knowledge | GPT-5.4 Pro | 74 vs 62 category score | High |
| Images and other media | GPT-5.4 Pro | 70 vs 61 category score | High |
| Chat quality (human preference) | – | Only GPT-6 Sol has an Arena rating (64 category score) | Not comparable |
| Lowest cost | GPT-6 Sol | $4.00 vs $67.50 per 1M blended; agentic coding session $0.160 vs $2.52 | – |
| Fastest first answer | GPT-5.4 Pro | 8.9 s (GPT-5.4 Pro) vs 72.1 s (GPT-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
- GPT-5.4 Pro and GPT-6 Sol (max) are neck and neck on quality (63.3 vs 62.9, within the ±4.9 margin).
- GPT-5.4 Pro is stronger in instruction following, knowledge, multimodal, reasoning.
- GPT-6 Sol (max) is stronger in agents & tools, coding, human preference, long context, maths.
- GPT-6 Sol (max) is 17× cheaper ($4.00 vs $67.50 per 1M blended).
- GPT-6 Sol (max) streams 20.2× faster (121 vs 6 tokens per second).
At a glance
| Spec | GPT-5.4 Pro | GPT-6 Sol |
|---|---|---|
| Developer | OpenAI | OpenAI |
| Released | 4 Mar 2026 | 22 Sep 2026 |
| Context window (tokens) | 1,050,000 | 1,050,000 |
| Compared at | GPT-5.4 Pro | GPT-6 Sol (max) |
| Open weights | No | No |
| Price in / out / cached input per 1M | $30.00 / $180.00 / – | $2.00 / $10.00 / $0.200 |
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-5.4 Pro | GPT-6 Sol (max) | Leader |
|---|---|---|---|
| Reasoning | 72.9 | 66.2 | GPT-5.4 Pro |
| Coding | – | 66.5 | not comparable |
| Agents & tools | – | 59.6 | not comparable |
| Maths | – | 68.5 | not comparable |
| Knowledge | 74.0 | 61.5 | GPT-5.4 Pro |
| Instruction following | 63.1 | – | not comparable |
| Human preference | – | 64.2 | not comparable |
| Multimodal | 69.8 | 60.7 | GPT-5.4 Pro |
| Long context | – | 66.6 | 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.
Not drawn, measured for fewer than two of these models: Coding, Agents & tools, Maths, Instruction following, Long context, Human preference.
Where sources disagree
Across the 0 benchmarks both have, GPT-5.4 Pro leads 0, GPT-6 Sol leads 0.
| Overall index | GPT-5.4 Pro | GPT-6 Sol (max) | Leader |
|---|---|---|---|
| BenchLeader Index | 63.3 | 62.9 | neck and neck |
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-5.4 Pro | GPT-6 Sol (max) |
|---|---|---|
| Blended price per 1M tokens | $67.50 | $4.00 |
| Input / output per 1M | $30.00 / $180.00 | $2.00 / $10.00 |
| Cached input per 1M | – | $0.200 |
| Price per task: chat reply | $0.066 | $0.0038 |
| Price per task: summarize a 30-page report | $0.468 | $0.030 |
| Price per task: code edit | $0.450 | $0.027 |
| Price per task: agentic coding session | $2.52 | $0.160 |
| Price per task: structured extraction | $0.096 | $0.0060 |
| Agentic coding session, input mostly cached | – | $0.079 |
| Cost per benchmark task (AA Index) | – | $2.47 |
| Output tokens per task (AA Index) | – | 54k |
| Of which reasoning | – | 35k |
| Time per task (AA Index) | – | 7 min |
| Output speed | 6 tok/s | 121 tok/s |
| Time to first answer | 8.9 s | 72.1 s |
| Time to a complete answer | – | 130.2 s |
Each model is compared at its best-ranked reasoning-effort setting. GPT-5.4 Pro scores 63.3 and takes 9 s to its first answer token; GPT-5.4 Pro (xhigh) scores 59.9 in 9 s. GPT-6 Sol (max) scores 62.9 and takes 72 s to its first answer token; GPT-6 Sol (xhigh) scores 58.6 in 24 s, GPT-6 Sol (high) scores 58.2 in 9 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
106 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-5.4 Pro | GPT-6 Sol (max) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 63.3 | 62.9 |
| Instruction following score | BenchLeader | 63.1 | – |
| Knowledge score | BenchLeader | 74.0 | 61.5 |
| Multimodal score | BenchLeader | 69.8 | 60.7 |
| Reasoning score | BenchLeader | 72.9 | 66.2 |
| Agents & tools score | BenchLeader | – | 59.6 |
| Coding score | BenchLeader | – | 66.5 |
| Human preference score | BenchLeader | – | 64.2 |
| Long context score | BenchLeader | – | 66.6 |
| Maths score | BenchLeader | – | 68.5 |
| Blended price $/M | BenchLeader | $67.50 | $4.00 |
| Output speed | BenchLeader | 6 tok/s | 121 tok/s |
| Time to first answer | BenchLeader | 8.9 s | 72.1 s |
| Context window | BenchLeader | 1,050,000 tokens | 1,050,000 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 94.6%† | 94.3% |
| Humanity's Last Exam | Scale AI / CAIS | 44.3% | – |
| SimpleBench | SimpleBench | 74.1% | – |
| Arena Hard Prompts | Arena (LMArena) | – | 1483 |
| LiveBench 1.0 Reasoning | LiveBench | – | 88.7% |
| Humanity's Last Exam (AA) | Artificial Analysis | – | 47.9% |
| HLE-Diamond (AA) | Artificial Analysis | – | 45.2% |
| ARC-AGI-1 | ARC Prize | 94.5%† | 95.5% |
| ARC-AGI-2 | ARC Prize | 83.3%† | 89.6% |
| ARC-AGI-3 | ARC Prize | – | 23.0% |
| CritPt | Artificial Analysis | 30.0%† | 30.9% |
| CritPt v2 hard subset (AA) | Artificial Analysis | – | 66.5% |
| MysteryMechanism | Vals AI | – | 30.2% |
| Chess Puzzles | Epoch AI Benchmarking Hub | 59.0%† | 56.0% |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | – | 56.0% |
| LMCA | Epoch AI Benchmarking Hub | – | 59.1% |
| DTBench | Epoch AI Benchmarking Hub | – | 97.3% |
| Coding | |||
| SciCode | SciCode | – | 57.6% |
| WeirdML | WeirdML | 57.4%† | – |
| FrontierCode | Cognition | – | 49.3% |
| Arena Coding | Arena (LMArena) | – | 1520 |
| Arena WebDev | Arena (LMArena) | – | 1674 |
| LiveBench 1.0 Coding | LiveBench | – | 81.8% |
| IOI | Vals AI | – | 82.6% |
| Code Migration | Vals AI | – | 57.2% |
Show all 106 benchmarks
| Metric | Publisher | GPT-5.4 Pro | GPT-6 Sol (max) |
|---|---|---|---|
| Coding | |||
| ProgramBench | Vals AI | – | 2.0% |
| Vibe Code Bench v1.1 | Vals AI | – | 87.8% |
| ALE-Bench | Epoch AI Benchmarking Hub | – | 2462 |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | – | 43.9% |
| GameBench 2 Overall | DuelLab GameBench 2 | – | 72.9† |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | – | 79.3† |
| Design Arena Website | Design Arena | – | 1285† |
| FrontierCode 2.0 (AA) | Artificial Analysis | – | 35.6% |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | – | 50.3% |
| APEX-Agents | Mercor | – | 54.3% |
| Arena Agent | Arena (LMArena) | – | 7 |
| LiveBench Agentic Coding | LiveBench | – | 52.9% |
| Terminal-Bench 2.1 (Vals) | Vals AI | – | 83.2% |
| ITBench SRE (AA) | Artificial Analysis | – | 49.4% |
| CyberBench | Vals AI | – | 78.0% |
| Finance Agent v2 | Vals AI | – | 49.0% |
| Harvey's Legal Agent Benchmark v1 | Vals AI | – | 1.7% |
| Legal Research Bench | Vals AI | – | 28.9% |
| SREBench | Vals AI | – | 30.5% |
| Tax Agent Bench | Vals AI | – | 15.0% |
| Terminal-Bench 4.0 (Vals) | Vals AI | – | 44.4% |
| Terminal-Bench Science | Vals AI | – | 30.0% |
| Arena Search | Arena (LMArena) | – | 1229 |
| Vending-Bench 2 | Andon Labs | – | 14427.9† |
| AutomationBench | Artificial Analysis | – | 61.6% |
| GDP.pdf (AA) | Artificial Analysis | – | 25.2% |
| Harvey LAB-AA v1.1 | Harvey | – | 3.6% |
| AA-Briefcase v1.1 | Artificial Analysis | – | 1476 |
| Design Arena Agentic | Design Arena | – | 1212† |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | – | 30.0% |
| CWE-Bench (AA) | Artificial Analysis | – | 64.2% |
| DeepSec-Bench (AA) | Artificial Analysis | – | 46.3% |
| CyberGym end-to-end (AA) | Artificial Analysis | – | 0.0% |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 82.5%† | 89.8% |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 58.5%† | 90.0% |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | – | 100.0% |
| ProofBench | Vals AI | – | 83.0%† |
| LiveBench Mathematics | LiveBench | – | 96.4% |
| MathArena Apex | MathArena | 69.8%† | – |
| Arena Maths | Arena (LMArena) | – | 1440 |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 46.3%† | 60.7% |
| LiveBench 1.0 Data Analysis | LiveBench | – | 81.2% |
| AA-Omniscience v1.1 | Artificial Analysis | – | 21.4 |
| PRBench Legal | Scale AI SEAL | – | 38.6%† |
| MultiNRC | Scale AI SEAL | 62.3% | – |
| BioMysteryBench | Vals AI | – | 74.8% |
| Excel Modeling Benchmark | Vals AI | – | 71.5% |
| MedCode | Vals AI | – | 47.1% |
| MedScribe | Vals AI | – | 82.0% |
| Public Benefits Bench v1.1 | Vals AI | – | 56.6% |
| EBR-bench | Epoch AI Benchmarking Hub | – | 53.3% |
| GDP.pdf | Epoch AI Benchmarking Hub | – | 26.4% |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | – | 51.1% |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | – | 39.1% |
| HealthBench Professional (AA) | OpenAI | – | 62.3% |
| Instruction following | |||
| LiveBench Language | LiveBench | – | 85.3% |
| LiveBench Instruction Following | LiveBench | – | 68.6% |
| MultiChallenge | Scale AI SEAL | 69.2% | – |
| TutorBench | Scale AI SEAL | 56.6% | – |
| Arena Instruction Following | Arena (LMArena) | – | 1448 |
| Human preference | |||
| Arena Text | Arena (LMArena) | – | 1457 |
| Arena Creative Writing | Arena (LMArena) | – | 1430 |
| Arena Multi-turn | Arena (LMArena) | – | 1466 |
| Arena Longer Queries | Arena (LMArena) | – | 1466 |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | – | 1232 |
| MMMU-Pro | Artificial Analysis | – | 83.0% |
| VISTA | Scale AI SEAL | 53.9% | – |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | – | 36.9%† |
| AA-3D | Artificial Analysis | – | 1131 |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | – | 83.7% |
| MLCR | Artificial Analysis | – | 33.9% |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 160.2 | 164.1† |
| LiveBench 1.0 | LiveBench | – | 79.3% |
| AA Intelligence Index v5.0 | Artificial Analysis | – | 44.2 |
| AA Intelligence Index v4.3.2 | Artificial Analysis | – | 47.6 |
| AA Progress Index v1 | Artificial Analysis | – | 334 |
| Vals RSI Index | Vals AI | – | 28.1% |
| Vals Science Index | Vals AI | – | 45.0% |
| AA Cyber Index | Artificial Analysis | – | 36.8 |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | 14.8% | 13.5%† |
| MASK | Scale AI SEAL | 91.7% | – |
Data as of 2026-11-09. Best configuration of each model; every score links to its source on the model pages.
DuelLab GameBench 2, release gb2-20261103-eaea31df94e6 (https://benchmarks.duellab.org/releases/gb2-20261103-eaea31df94e6/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.
What changed
- GPT-6 Sol (max): BenchLeader Index 63.5 → 62.9.
- GPT-6 Sol (max): 2 score revisions.
- GPT-6 Sol (max): 1 score revision.
- GPT-6 Sol (max): 1 score revision.
- GPT-6 Sol (max): 6 new results (AA Intelligence Index v5.0, AA-Omniscience v1.1, CritPt v2 hard subset (AA)…).
- GPT-6 Sol (max): 1 score revision.
- GPT-6 Sol (max): 1 score revision.
- GPT-6 Sol (max): BenchLeader Index 64.1 → 63.5.
- GPT-6 Sol (max): 2 new results (AA Progress Index v1, HLE-Diamond (AA)).
- GPT-5.4 Pro: BenchLeader Index 63.6 → 63.1.
Related comparisons
- GPT-5.4 Pro vs Claude Fable 5.2
- GPT-5.4 Pro vs Claude Opus 5.5
- GPT-5.4 Pro vs Gemini 4 Carbon
- GPT-6 Sol vs Claude Fable 5.2
- GPT-6 Sol vs Claude Opus 5.5
- GPT-6 Sol vs Gemini 4 Carbon
- GPT-6 Sol vs GPT-6 Astra
- GPT-5.3-Codex vs GPT-6 Sol
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
GPT-5.4 Pro vs GPT-6 Sol: questions
- Is GPT-5.4 Pro better than GPT-6 Sol?
- GPT-5.4 Pro and GPT-6 Sol (max) are neck and neck on quality (63.3 vs 62.9, within the ±4.9 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 9 Nov 2026, so check the category scores for your use.
- GPT-5.4 Pro vs GPT-6 Sol: which is cheaper, and will that change?
- GPT-6 Sol is cheaper today: $4.00 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-5.4 Pro or GPT-6 Sol?
- GPT-6 Sol streams 3×+ faster (121 vs 6 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-5.4 Pro answers first: 8.9 s against 72.1 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.
More questions (1)
- When was GPT-6 Sol released?
- GPT-6 Sol was released on 22 Sep 2026.