Gemini 2.5 Pro Preview 0325 vs GPT-6.1 Sol
Full profiles: Gemini 2.5 Pro Preview 0325 (Google) and GPT-6.1 Sol (OpenAI): every benchmark, price and rank.
Updated · Data from 17 sources
As of 22 Nov 2026, GPT-6.1 Sol is ahead of Gemini 2.5 Pro Preview 0325 on quality (65.8 vs 59.7 on the BenchLeader Index). Choose Gemini 2.5 Pro Preview 0325 for long context (73 vs 66) and multimodal (71 vs 65); choose GPT-6.1 Sol for reasoning (70 vs 52), knowledge (70 vs 56), and maths (71 vs 59).
Key facts (as of 22 Nov 2026)
- Gemini 2.5 Pro Preview 0325 scores 59.7 on the BenchLeader Index and GPT-6.1 Sol scores 65.8 (BenchLeader, 22 Nov 2026).
- GPT-6.1 Sol costs $4.00 per 1M tokens blended (list price, 22 Nov 2026).
- Of the 3 benchmarks both models have, GPT-6.1 Sol leads 3 (BenchLeader, 22 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 |
|---|---|---|---|
| Coding | GPT-6.1 Sol | 70 vs 61 category score | High |
| Maths | GPT-6.1 Sol | 71 vs 59 category score | High |
| Reasoning | GPT-6.1 Sol | 70 vs 52 category score; GPQA Diamond 95.4% vs 83.8% | High |
| Knowledge | GPT-6.1 Sol | 70 vs 56 category score | High |
| Long documents | Gemini 2.5 Pro Preview 0325 | 73 vs 66 category score | Medium |
| Images and other media | Gemini 2.5 Pro Preview 0325 | 71 vs 65 category score | Medium |
| Chat quality (human preference) | – | Only GPT-6.1 Sol has an Arena rating (67 category score) | Not comparable |
| High volume on a budget | Neither flagship | A smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs | – |
Key differences
- GPT-6.1 Sol (max) leads on quality: 65.8 vs 59.7.
- Gemini 2.5 Pro Preview 0325 is stronger in long context, multimodal.
- GPT-6.1 Sol (max) is stronger in coding, knowledge, maths, reasoning.
At a glance
| Spec | Gemini 2.5 Pro Preview 0325 | GPT-6.1 Sol |
|---|---|---|
| Developer | OpenAI | |
| Released | 25 Mar 2025 | 29 Sep 2026 |
| Context window (tokens) | 1,000,000 | 1,050,000 |
| Compared at | Gemini 2.5 Pro Preview 0325 | GPT-6.1 Sol (max) |
| Open weights | No | No |
| Price in / out / cached input per 1M | – | $2.00 / $10.00 / $0.100 |
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 | Gemini 2.5 Pro Preview 0325 | GPT-6.1 Sol (max) | Leader |
|---|---|---|---|
| Reasoning | 52.1 | 70.0 | GPT-6.1 Sol |
| Coding | 61.1 | 70.1 | GPT-6.1 Sol |
| Agents & tools | – | 62.7 | not comparable |
| Maths | 58.9 | 71.1 | GPT-6.1 Sol |
| Knowledge | 56.2 | 70.2 | GPT-6.1 Sol |
| Instruction following | 57.9 | – | not comparable |
| Human preference | – | 67.2 | not comparable |
| Multimodal | 70.8 | 65.4 | Gemini 2.5 Pro Preview 0325 |
| Long context | 72.8 | 66.2 | Gemini 2.5 Pro Preview 0325 |
| Composite | – | 65.5 | 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: Agents & tools, Instruction following, Human preference.
Where sources disagree
Across the 3 benchmarks both have, Gemini 2.5 Pro Preview 0325 leads 0, GPT-6.1 Sol leads 3. Every overall index that rates both puts GPT-6.1 Sol ahead.
| Overall index | Gemini 2.5 Pro Preview 0325 | GPT-6.1 Sol (max) | Leader |
|---|---|---|---|
| BenchLeader Index | 59.7 | 65.8 | GPT-6.1 Sol |
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 | Gemini 2.5 Pro Preview 0325 | GPT-6.1 Sol (max) |
|---|---|---|
| Blended price per 1M tokens | – | $4.00 |
| Input / output per 1M | – / – | $2.00 / $10.00 |
| Cached input per 1M | – | $0.100 |
| Price per task: chat reply | – | $0.0038 |
| Price per task: summarize a 30-page report | – | $0.030 |
| Price per task: code edit | – | $0.027 |
| Price per task: agentic coding session | – | $0.160 |
| Price per task: structured extraction | – | $0.0060 |
| Agentic coding session, input mostly cached | – | $0.074 |
| Cost per benchmark task (AA Index) | – | $1.27 |
| Output tokens per task (AA Index) | – | 68k |
| Of which reasoning | – | 49k |
| Time per task (AA Index) | – | 24 min |
| Output speed | – | 47 tok/s |
| Time to first answer | – | 121.6 s |
| Time to a complete answer, last measured 13 Nov 2026 | – | 429.6 s |
Each model is compared at its best-ranked reasoning-effort setting. Gemini 2.5 Pro Preview 0325 scores 59.7. GPT-6.1 Sol (max) scores 65.8 and takes 122 s to its first answer token; GPT-6.1 Sol (high) scores 63.8 in 26 s, GPT-6.1 Sol (xhigh) scores 62.3 in 63 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
188 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 | Gemini 2.5 Pro Preview 0325 | GPT-6.1 Sol (max) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 59.7 | 65.8 |
| Coding score | BenchLeader | 61.1 | 70.1 |
| Instruction following score | BenchLeader | 57.9 | – |
| Knowledge score | BenchLeader | 56.2 | 70.2 |
| Long context score | BenchLeader | 72.8 | 66.2 |
| Maths score | BenchLeader | 58.9 | 71.1 |
| Multimodal score | BenchLeader | 70.8 | 65.4 |
| Reasoning score | BenchLeader | 52.1 | 70.0 |
| Agents & tools score | BenchLeader | – | 62.7 |
| Composite score | BenchLeader | – | 65.5 |
| Human preference score | BenchLeader | – | 67.2 |
| Blended price $/M | BenchLeader | – | $4.00 |
| Output speed | BenchLeader | – | 47 tok/s |
| Time to first answer | BenchLeader | – | 121.6 s |
| Context window | BenchLeader | 1,000,000 tokens | 1,050,000 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 83.8% | 95.4% |
| Humanity's Last Exam | Scale AI / CAIS | 18.2% | – |
| SimpleBench | SimpleBench | 51.6% | 82.9%† |
| Arena Hard Prompts | Arena (LMArena) | – | 1507 |
| LiveBench 2.0 Reasoning | LiveBench | – | 92.6% |
| LiveBench 1.0 Reasoning | LiveBench | – | 92.6% |
| GPQA Diamond (AA) | Artificial Analysis | 83.6% | – |
| Humanity's Last Exam (AA) | Artificial Analysis | 18.0% | 52.9% |
| HLE-Diamond (AA) | Artificial Analysis | – | 58.8% |
| GPQA Diamond (Vals) | Vals AI | 80.8% | – |
| GPQA Diamond (HELM) | HELM Capabilities | 74.9% | – |
| ARC-AGI-1 | ARC Prize | – | 96.5% |
| ARC-AGI-2 | ARC Prize | – | 94.2% |
| ARC-AGI-3 | ARC Prize | – | 96.2% |
| CritPt | Artificial Analysis | – | 31.7% |
| CritPt v2 hard subset (AA) | Artificial Analysis | – | 69.5% |
| MysteryMechanism | Vals AI | – | 46.4% |
| HLE-Diamond (Scale) | Scale AI SEAL | – | 53.6%† |
| HLE Text-Only (Scale) | Scale AI SEAL | 18.4% | – |
| Arena Expert | Arena (LMArena) | – | 1528 |
| Chess Puzzles | Epoch AI Benchmarking Hub | – | 68.0% |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | – | 80.0% |
| LMCA | Epoch AI Benchmarking Hub | – | 62.8% |
| DTBench | Epoch AI Benchmarking Hub | – | 96.5% |
| ForecastBench | ForecastBench | 64.0% | – |
Show all 188 benchmarks
| Metric | Publisher | Gemini 2.5 Pro Preview 0325 | GPT-6.1 Sol (max) |
|---|---|---|---|
| Coding | |||
| SciCode | SciCode | – | 54.2% |
| FrontierCode | Cognition | – | 50.2%† |
| Arena Coding | Arena (LMArena) | – | 1545 |
| Arena WebDev | Arena (LMArena) | – | 1743 |
| LiveBench 2.0 Coding | LiveBench | – | 82.1% |
| LiveBench 1.0 Coding | LiveBench | – | 80.4% |
| LiveCodeBench | Vals AI | 79.2% | – |
| IOI | Vals AI | – | 96.9% |
| Aider Polyglot | Aider polyglot leaderboard | 72.9% | – |
| Code Migration | Vals AI | – | 65.1% |
| Code Migration v1.1 | Vals AI | – | 77.3% |
| ProgramBench | Vals AI | – | 3.0% |
| SWE-bench Multimodal | Vals AI | – | 43.5% |
| Vibe Code Bench v1.1 | Vals AI | – | 88.9% |
| SWE Atlas v1.1 | Scale AI SEAL | – | 65.9% |
| SWE Atlas v1.1: Codebase QnA | Scale AI SEAL | – | 71.0% |
| SWE Atlas v1.1: Test Writing | Scale AI SEAL | – | 66.7% |
| SWE Atlas v1.1: Refactoring | Scale AI SEAL | – | 60.0% |
| SWE-Bench Pro V2 | Scale AI SEAL | – | 96.1%† |
| MirrorCode | Epoch AI Benchmarking Hub | – | 61.1% |
| CadEval | Epoch AI Benchmarking Hub | 64.0% | – |
| ALE-Bench | Epoch AI Benchmarking Hub | – | 2743.8 |
| WeirdML v3 | WeirdML | – | 38.3%† |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | – | 56.1% |
| Startrise Frontend | Startrise | – | 78.6%† |
| GameBench 2 Overall | DuelLab GameBench 2 | – | 85† |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | – | 91.8† |
| Design Arena Website | Design Arena | – | 1311† |
| Design Arena Code | Design Arena | – | 1353† |
| FrontierCode 1.1 (AA) | Artificial Analysis | – | 49.1% |
| FrontierCode 2.0 (AA) | Artificial Analysis | – | 40.6% |
| LiveCodeBench (AA) | Artificial Analysis | 77.8% | – |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | – | 60.9% |
| APEX-Agents | Mercor | – | 60.0% |
| Arena Agent | Arena (LMArena) | – | 11.3 |
| LiveBench Long Agentic | LiveBench | – | 64.7% |
| LiveBench Browser | LiveBench | – | 93.3% |
| LiveBench Agentic Coding | LiveBench | – | 54.5% |
| HiL-Bench | Scale AI SEAL | – | 62.3%† |
| GDPval-AA v2.1, normalised score | Artificial Analysis | – | 54.8% |
| GDPval-AA v2.1 | Artificial Analysis | – | 1607 |
| Analyst Agent (AA) | Artificial Analysis | – | 50.0% |
| CyberBench | Vals AI | – | 39.3% |
| Finance Agent v2 | Vals AI | – | 52.0% |
| Finance Agent v2.1 | Vals AI | – | 61.8% |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | – | 6.3% |
| Harvey's Legal Agent Benchmark v1 | Vals AI | – | 5.4% |
| Legal Research Bench | Vals AI | – | 38.5% |
| Robo-bench | Vals AI | – | 28.3% |
| SREBench | Vals AI | – | 50.8% |
| Tax Agent Bench | Vals AI | – | 21.8% |
| Terminal-Bench 4.0 (Vals) | Vals AI | – | 55.0% |
| Terminal-Bench Science | Vals AI | – | 52.9% |
| Arena Search | Arena (LMArena) | – | 1249 |
| Arena Agent Task Completion | Arena (LMArena) | – | 11.6 |
| Arena Search Factuality | Arena (LMArena) | – | 1236 |
| BALROG | BALROG | 43.3% | – |
| PostTrainBench | Epoch AI Benchmarking Hub | – | 38.8% |
| GBAEval | Epoch AI Benchmarking Hub | – | 81.9%† |
| Vending-Bench 2 | Andon Labs | – | 12860.6† |
| SpireClimb | Epoch AI Benchmarking Hub | – | 23.8% |
| AutomationBench | Artificial Analysis | – | 64.9% |
| GDP.pdf (AA) | Artificial Analysis | – | 31.0% |
| Harvey LAB-AA v1.1 | Harvey | – | 6.9% |
| AA-Briefcase v1.1 | Artificial Analysis | – | 1557 |
| GDPx | GDPx by SemiAnalysis | – | 8.4% |
| Design Arena Agentic | Design Arena | – | 1356 |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | – | 58.1% |
| MKA (AA) | Artificial Analysis | – | 47.7% |
| FACTS Search | – | 92.8%† | |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | – | 93.7% |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | – | 100.0% |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | – | 100.0% |
| MATH Level 5 | Epoch AI Benchmarking Hub | 95.6% | – |
| ProofBench | Vals AI | – | 99.0%† |
| LiveBench Mathematics | LiveBench | – | 96.8% |
| AIME (Vals) | Vals AI | 85.8% | – |
| ArXivMath | MathArena | – | 92.8% |
| BrokenArXiv | MathArena | – | 83.1% |
| Omni-MATH (HELM) | HELM Capabilities | 41.6% | – |
| MATH 500 | Vals AI | 95.2% | – |
| Arena Maths | Arena (LMArena) | – | 1499 |
| FrontierMath Erdős | Epoch AI Benchmarking Hub | – | 4.4% |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | – | 73.9% |
| LiveBench 2.0 Data Analysis | LiveBench | – | 82.7% |
| LiveBench Research | LiveBench | – | 90.0% |
| LiveBench 1.0 Data Analysis | LiveBench | – | 82.7% |
| AA-Omniscience v1.1 | Artificial Analysis | – | 42.0 |
| MMLU-Pro | Vals AI | 84.1% | – |
| LegalBench | Vals AI | 84.3% | – |
| CorpFin | Vals AI | 59.8% | – |
| TaxEval | Vals AI | 72.9% | – |
| MedQA | Vals AI | 93.1% | – |
| PRBench Finance | Scale AI SEAL | – | 46.2%† |
| PRBench Legal | Scale AI SEAL | – | 47.9%† |
| MMLU-Pro (HELM) | HELM Capabilities | 86.3% | – |
| BioMysteryBench | Vals AI | – | 79.6% |
| ClaimBench | Vals AI | – | 100.0% |
| Excel Modeling Benchmark | Vals AI | – | 70.8% |
| Excel Modeling Benchmark v1.1 | Vals AI | – | 71.1% |
| MedCode | Vals AI | – | 48.8% |
| MedScribe | Vals AI | – | 86.5% |
| Public Benefits Bench v1.1 | Vals AI | – | 59.3% |
| Access to Justice Benchmark | Vals AI | – | 65.8% |
| Financial Coaching Bench | Vals AI | – | 68.5% |
| Immigration Bench | Vals AI | – | 67.8% |
| Arena Text Factuality | Arena (LMArena) | – | 1470 |
| EBR-bench | Epoch AI Benchmarking Hub | – | 54.3% |
| GDP.pdf | Epoch AI Benchmarking Hub | – | 51.6% |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | – | 61.8% |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | – | 48.1% |
| HealthBench Professional (AA) | OpenAI | – | 65.1% |
| FACTS Parametric | – | 83.8%† | |
| Instruction following | |||
| LiveBench Language | LiveBench | – | 90.1% |
| LiveBench Instruction Following | LiveBench | – | 74.2% |
| MultiChallenge | Scale AI SEAL | – | 82.0%† |
| IFEval (HELM) | HELM Capabilities | 84.0% | – |
| WildBench (HELM) | HELM Capabilities | 85.7% | – |
| Arena Instruction Following | Arena (LMArena) | – | 1484 |
| Human preference | |||
| Arena Text | Arena (LMArena) | – | 1483 |
| EQ-Bench 4 | EQ-Bench | – | 1272† |
| EQ-Bench Creative Writing v3 | EQ-Bench | 1396 | – |
| EQ-Bench Longform Writing | EQ-Bench | 58.8 | – |
| Arena Creative Writing | Arena (LMArena) | – | 1450 |
| Arena Multi-turn | Arena (LMArena) | – | 1487 |
| Arena Longer Queries | Arena (LMArena) | – | 1489 |
| Lech Mazur Creative Writing | Lech Mazur | 80.5% | – |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | – | 1284 |
| LiveBench Design | LiveBench | – | 79.6% |
| MMMU-Pro | Artificial Analysis | – | 86.0% |
| VISTA | Scale AI SEAL | 54.6% | – |
| MMMU-Pro (Vals) | Vals AI | 81.3% | – |
| MortgageTax | Vals AI | 67.2% | – |
| SAGE | Vals AI | – | 90.5% |
| Humanity's Sixth Sense | Scale AI SEAL | – | 46.6% |
| GeoBench | GeoBench | 84.0% | – |
| VPCT | Epoch AI Benchmarking Hub | 48.0% | – |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | – | 43.2%† |
| Furniture Assembly | Epoch AI Benchmarking Hub | – | 80.0% |
| VIALS-AA | Handshake AI | – | 59.0% |
| Code2Video-AA | Artificial Analysis | – | 1369 |
| AA-3D | Artificial Analysis | – | 1121 |
| FACTS Multimodal | – | 52.6%† | |
| Long context | |||
| Fiction.LiveBench 120k | Fiction.live | 90.6% | – |
| AA-LCR v1.1 | Artificial Analysis | – | 83.0% |
| MLCR | Artificial Analysis | – | 38.3% |
| FACTS Grounding | – | 78.0%† | |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 144.0 | 168.6† |
| LiveBench 2.0 | LiveBench | – | 81.2% |
| LiveBench 1.0 | LiveBench | – | 81.6% |
| AA Intelligence Index v5.0.1 | Artificial Analysis | – | 54.6 |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 15.0 | 51.8 |
| AA Progress Index v1 | Artificial Analysis | 245.9 | 348.5 |
| Vals Index | Vals AI | – | 63.9 |
| HELM Capabilities mean | HELM Capabilities | 74.5% | – |
| Vals Finance Index | Vals AI | – | 55.8% |
| Vals RSI Index | Vals AI | – | 26.6% |
| Vals Science Index | Vals AI | – | 59.6% |
| Vals Router Index | Vals AI | – | 63.9%† |
| Vals Legal Index | Vals AI | – | 68.7% |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | 54.9% | 14.7%† |
| MASK | Scale AI SEAL | 55.9% | – |
| DistressBench | Scale AI SEAL | – | 74.2%† |
Data as of 2026-11-22. Best configuration of each model; every score links to its source on the model pages.
DuelLab GameBench 2, release gb2-20261119-1d7fd529faf6 (https://benchmarks.duellab.org/releases/gb2-20261119-1d7fd529faf6/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.
What changed
- GPT-6.1 Sol (max): 1 score revision.
- GPT-6.1 Sol (max): 4 new results (SWE Atlas v1.1, SWE Atlas v1.1: Codebase QnA, SWE Atlas v1.1: Test Writing…); 1 score revision.
- GPT-6.1 Sol (max): 1 score revision.
- GPT-6.1 Sol (max): 2 score revisions.
- GPT-6.1 Sol (max): BenchLeader Index 66.9 → 66.1.
- GPT-6.1 Sol (max): 1 score revision.
- GPT-6.1 Sol (max): 3 score revisions.
- GPT-6.1 Sol (max): 8 new results (LiveBench 2.0, LiveBench Long Agentic, LiveBench 2.0 Reasoning…); 1 score revision.
- GPT-6.1 Sol (max): 1 score revision.
- GPT-6.1 Sol (max): 1 score revision.
Related comparisons
- GPT-6.1 Sol vs Claude Fable 5.2
- GPT-6.1 Sol vs Gemini 4 Carbon
- GPT-6.1 Sol vs GPT-6.2 Astra
- GPT-6.1 Sol vs Gemini 4 Neon
- Gemini 2.5 Pro Preview 0325 vs Claude Opus 5.5
- Gemini 2.5 Pro Preview 0325 vs Claude Fable 5.1
- Gemini 2.5 Pro Preview 0325 vs GPT-5.6 Sol
- Gemini 2.5 Pro Preview 0325 vs Claude Fable 5
Rankings: Best LLM overall · Best LLM for coding · Best LLM for agents · Best cheap LLMs
Gemini 2.5 Pro Preview 0325 vs GPT-6.1 Sol: questions
- Is GPT-6.1 Sol better than Gemini 2.5 Pro Preview 0325?
- GPT-6.1 Sol (max) leads on quality: 65.8 vs 59.7. The BenchLeader Index combines every independent quality benchmark; GPT-6.1 Sol (max) is ahead overall as of 22 Nov 2026, but check the category scores for your use.
- Is Gemini 2.5 Pro Preview 0325 or GPT-6.1 Sol better for coding?
- GPT-6.1 Sol scores higher in coding (70 vs 61 on the category index, where 50 is average).
- Which is better for long documents?
- Gemini 2.5 Pro Preview 0325 scores higher on long-context benchmarks (73 vs 66). Both take about 1.1M tokens: Gemini 2.5 Pro Preview 0325 1,000,000, GPT-6.1 Sol 1,050,000.
- Do independent benchmarks agree on Gemini 2.5 Pro Preview 0325 vs GPT-6.1 Sol?
- Across the 3 benchmarks both have, Gemini 2.5 Pro Preview 0325 leads 0, GPT-6.1 Sol leads 3. Every overall index that rates both puts GPT-6.1 Sol ahead.
- When was GPT-6.1 Sol released?
- GPT-6.1 Sol was released on 29 Sep 2026.