Gemini 3.7 Flash vs o3
Full profiles: Gemini 3.7 Flash (Google) and o3 (OpenAI): every benchmark, price and rank.
Updated · Data from 18 sources
As of 2 Nov 2026, Gemini 3.7 Flash and o3 are neck and neck on quality (62.2 vs 61.0 on the BenchLeader Index, inside the ±5.0 margin), and Gemini 3.7 Flash is 2.3× cheaper at $1.50 vs $3.50 per 1M tokens blended. Choose Gemini 3.7 Flash for multimodal (67 vs 57), knowledge (66 vs 56), and reasoning (68 vs 61) and fast first answers (2.4 s vs 6.8 s); choose o3 for agents & tools (70 vs 48) and maths (71 vs 63), where it also streams ~1.5× faster.
Key facts (as of 2 Nov 2026)
- Gemini 3.7 Flash scores 62.2 on the BenchLeader Index and o3 scores 61.0 (BenchLeader, 2 Nov 2026).
- Gemini 3.7 Flash costs $1.50 per 1M tokens blended (list price, 2 Nov 2026).
- o3 costs $3.50 per 1M tokens blended (list price, 2 Nov 2026).
- o3 streams ~1.5× faster than Gemini 3.7 Flash (Artificial Analysis, 7-day median, 2 Nov 2026).
- Of the 15 benchmarks both models have, Gemini 3.7 Flash leads 15 (BenchLeader, 2 Nov 2026).
Gemini 3.7 Flash benchmarks 
o3 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 |
|---|---|---|---|
| Coding | Either | 63 vs 62 category score; Arena Coding 1520 vs 1460 | Either |
| Agents & tool use | o3 | 70 vs 48 category score | High |
| Maths | o3 | 71 vs 63 category score; Arena Maths 1448 vs 1503 | High |
| Reasoning | Gemini 3.7 Flash | 68 vs 61 category score; Arena Hard Prompts 1509 vs 1441 | Medium |
| Knowledge | Gemini 3.7 Flash | 66 vs 56 category score | High |
| Long documents | Gemini 3.7 Flash | 66 vs 62 category score; AA-LCR v1.1 81.7% vs 74.7% | Medium |
| Images and other media | Gemini 3.7 Flash | 67 vs 57 category score; Arena Vision 1314 vs 1214 | High |
| Chat quality (human preference) | Gemini 3.7 Flash | 68 vs 61 on Arena votes | Medium |
| Lowest cost | Gemini 3.7 Flash | $1.50 vs $3.50 per 1M blended; agentic coding session $0.060 vs $0.152 | – |
| Fastest first answer | Gemini 3.7 Flash | 2.4 s (Gemini 3.7 Flash (high)) vs 6.8 s (o3) 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
- Gemini 3.7 Flash (high) and o3 are neck and neck on quality (62.2 vs 61.0, within the ±5.0 margin).
- Gemini 3.7 Flash (high) is stronger in coding, human preference, knowledge, long context, multimodal, reasoning.
- o3 is stronger in agents & tools, maths, instruction following.
- Gemini 3.7 Flash (high) is 2.3× cheaper ($1.50 vs $3.50 per 1M blended).
- o3 streams 1.8× faster (160 vs 91 tokens per second).
At a glance
| Spec | Gemini 3.7 Flash | o3 |
|---|---|---|
| Developer | OpenAI | |
| Released | 13 Aug 2026 | 16 Apr 2025 |
| Context window (tokens) | 1,048,576 | 200,000 |
| Compared at | Gemini 3.7 Flash (high) | o3 |
| Open weights | No | No |
| Price in / out / cached input per 1M | $0.750 / $3.75 / $0.075 | $2.00 / $8.00 / $0.500 |
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 3.7 Flash (high) | o3 | Leader |
|---|---|---|---|
| Reasoning | 68.3 | 60.9 | Gemini 3.7 Flash |
| Coding | 62.7 | 61.8 | level |
| Agents & tools | 47.7 | 70.3 | o3 |
| Maths | 63.0 | 70.5 | o3 |
| Knowledge | 66.2 | 56.1 | Gemini 3.7 Flash |
| Instruction following | – | 65.1 | not comparable |
| Human preference | 68.2 | 61.1 | Gemini 3.7 Flash |
| Multimodal | 67.3 | 56.7 | Gemini 3.7 Flash |
| Long context | 65.7 | 62.1 | Gemini 3.7 Flash |
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: Instruction following.
Where sources disagree
Across the 15 benchmarks both have, Gemini 3.7 Flash leads 15, o3 leads 0. Every overall index that rates both puts Gemini 3.7 Flash ahead.
| Overall index | Gemini 3.7 Flash (high) | o3 | Leader |
|---|---|---|---|
| BenchLeader Index | 62.2 | 61.0 | neck and neck |
| Arena Text | 1490 | 1432 | Gemini 3.7 Flash |
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 3.7 Flash (high) | o3 |
|---|---|---|
| Blended price per 1M tokens | $1.50 | $3.50 |
| Input / output per 1M | $0.750 / $3.75 | $2.00 / $8.00 |
| Cached input per 1M | $0.075 | $0.500 |
| Price per task: chat reply | $0.0014 | $0.0032 |
| Price per task: summarize a 30-page report | $0.011 | $0.029 |
| Price per task: code edit | $0.010 | $0.024 |
| Price per task: agentic coding session | $0.060 | $0.152 |
| Price per task: structured extraction | $0.0023 | $0.0056 |
| Agentic coding session, input mostly cached | $0.030 | $0.085 |
| Output speed | 91 tok/s | 160 tok/s |
| Time to first answer | 2.4 s | 6.8 s |
| Time to a complete answer | – | 9.9 s |
Each model is compared at its best-ranked reasoning-effort setting. Gemini 3.7 Flash (high) scores 62.2 and takes 2 s to its first answer token; Gemini 3.7 Flash (medium) scores 60.3 in 2 s, Gemini 3.7 Flash (low) scores 57.5 in 2 s. o3 scores 61.0 and takes 7 s to its first answer token; o3 (high) scores 53.8 in 7 s, o3 (medium) scores 53.3 in 7 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
138 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 3.7 Flash (high) | o3 |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 62.2 | 61.0 |
| Agents & tools score | BenchLeader | 47.7 | 70.3 |
| Coding score | BenchLeader | 62.7 | 61.8 |
| Human preference score | BenchLeader | 68.2 | 61.1 |
| Knowledge score | BenchLeader | 66.2 | 56.1 |
| Long context score | BenchLeader | 65.7 | 62.1 |
| Maths score | BenchLeader | 63.0 | 70.5 |
| Multimodal score | BenchLeader | 67.3 | 56.7 |
| Reasoning score | BenchLeader | 68.3 | 60.9 |
| Instruction following score | BenchLeader | – | 65.1 |
| Blended price $/M | BenchLeader | $1.50 | $3.50 |
| Output speed | BenchLeader | 91 tok/s | 160 tok/s |
| Time to first answer | BenchLeader | 2.4 s | 6.8 s |
| Context window | BenchLeader | 1,048,576 tokens | 200,000 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 94.8% | 81.8%† |
| Humanity's Last Exam | Scale AI / CAIS | – | 20.3%† |
| SimpleBench | SimpleBench | – | 53.1%† |
| Arena Hard Prompts | Arena (LMArena) | 1509 | 1441 |
| LiveBench 1.0 Reasoning | LiveBench | 87.8% | – |
| GPQA Diamond (AA) | Artificial Analysis | 94.5% | 82.7% |
| Humanity's Last Exam (AA) | Artificial Analysis | 47.9% | 20.1% |
| GPQA Diamond (Vals) | Vals AI | 93.9% | 84.1%† |
| Kagi LLM Benchmark | Kagi LLM Benchmark | – | 67.6% |
| GPQA Diamond (HELM) | HELM Capabilities | – | 75.3% |
| ARC-AGI-1 | ARC Prize | 95.5% | 60.8%† |
| ARC-AGI-2 | ARC Prize | 84.6% | 6.5%† |
| CritPt | Artificial Analysis | 14.3% | 1.1% |
| SciPredict | Scale AI SEAL | – | 17.9% |
| Chess Puzzles | Epoch AI Benchmarking Hub | 66.0% | 36.0%† |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 37.0% | 29.0%† |
| CL-bench | Epoch AI Benchmarking Hub | – | 17.8%† |
| LMCA | Epoch AI Benchmarking Hub | 50.4% | 39.7%† |
| DTBench | Epoch AI Benchmarking Hub | 96.8% | 84.8%† |
| ForecastBench | ForecastBench | 66.2% | 64.6% |
| Coding | |||
| SWE-bench Verified (Epoch) | Epoch AI Benchmarking Hub | – | 62.3%† |
| SciCode | SciCode | 57.2% | – |
| WeirdML | WeirdML | – | 52.4%† |
| FrontierCode | Cognition | 43.6%† | – |
| GSO-Bench | GSO-Bench | – | 8.8%† |
Show all 138 benchmarks
| Metric | Publisher | Gemini 3.7 Flash (high) | o3 |
|---|---|---|---|
| Coding | |||
| Arena Coding | Arena (LMArena) | 1520 | 1460 |
| Arena WebDev | Arena (LMArena) | 1590 | – |
| LiveBench 1.0 Coding | LiveBench | 78.9% | – |
| LiveCodeBench | Vals AI | 88.7% | 83.9%† |
| IOI | Vals AI | 67.8% | – |
| SWE-bench (Vals) | Vals AI | 80.8% | – |
| Aider Polyglot | Aider polyglot leaderboard | – | 81.3% |
| SWE-bench Verified (bash only) | SWE-bench | – | 58.4% |
| SWE-bench Verified (any scaffold) | SWE-bench | – | 58.4% |
| Code Migration | Vals AI | 34.8% | – |
| ProgramBench | Vals AI | 0.0% | – |
| Vibe Code Bench v1.1 | Vals AI | 70.4% | – |
| MirrorCode | Epoch AI Benchmarking Hub | 41.1% | – |
| CadEval | Epoch AI Benchmarking Hub | – | 74.0%† |
| DeepSWE v1.1 | Epoch AI Benchmarking Hub | 65.3% | – |
| ALE-Bench | Epoch AI Benchmarking Hub | 904.3 | 933.5† |
| FrontierSWE | Epoch AI Benchmarking Hub | 20.3% | – |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 13.6% | – |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | 85.8% | – |
| GameBench 2 Overall | DuelLab GameBench 2 | – | 36.2 |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | – | 32.0† |
| LiveCodeBench (AA) | Artificial Analysis | – | 80.8% |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | 11.2% | – |
| GDPval | OpenAI | – | 30.8%† |
| Remote Labor Index | Scale AI / CAIS | 5.0%† | – |
| APEX-Agents | Mercor | 67.8%† | – |
| Arena Agent | Arena (LMArena) | -1.3 | – |
| LiveBench Agentic Coding | LiveBench | 58.3% | – |
| Terminal-Bench Hard | Artificial Analysis | – | 37.1% |
| τ²-Bench Telecom (AA) | Artificial Analysis | – | 80.7% |
| Terminal-Bench 2.1 (Vals) | Vals AI | 77.5% | – |
| BFCL Overall | Berkeley Function Calling Leaderboard | – | 63.0% |
| τ³-Banking (AA) | Artificial Analysis | 32.8% | – |
| Analyst Agent (AA) | Artificial Analysis | 60.0% | – |
| CyberBench | Vals AI | 43.8% | – |
| Finance Agent v2 | Vals AI | 59.0% | – |
| Harvey's Legal Agent Benchmark v1 | Vals AI | 8.8% | – |
| Legal Research Bench | Vals AI | 34.6% | – |
| SkillsBench | Vals AI | 65.9% | – |
| SREBench | Vals AI | 4.6% | – |
| Tax Agent Bench | Vals AI | 22.8% | – |
| Terminal-Bench 4.0 (Vals) | Vals AI | 12.1% | – |
| Terminal-Bench Science | Vals AI | 7.1% | – |
| DeepResearch Bench | DeepResearch Bench | – | 45.2%† |
| METR Time Horizons | METR | – | 63.6% |
| AutomationBench | Artificial Analysis | 62.0% | – |
| GDP.pdf (AA) | Artificial Analysis | 23.6% | – |
| EnterpriseOps-Gym | Artificial Analysis | 50.4%† | – |
| BrowseComp-Plus | BrowseComp-Plus | – | 50.5% |
| FACTS Search | 80.9%† | – | |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 71.6% | 33.3%† |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 36.6% | – |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 97.2% | 83.9%† |
| MATH Level 5 | Epoch AI Benchmarking Hub | – | 97.8%† |
| ProofBench | Vals AI | 58.0%† | – |
| LiveBench Mathematics | LiveBench | 93.5% | – |
| AIME (Vals) | Vals AI | – | 85.3%† |
| MGSM | Vals AI | – | 91.8%† |
| IMO 2025 | MathArena | – | 16.7%† |
| Omni-MATH (HELM) | HELM Capabilities | – | 71.4% |
| MATH 500 | Vals AI | – | 94.6%† |
| Arena Maths | Arena (LMArena) | 1503 | 1448 |
| AIME 2025 (AA) | Artificial Analysis | – | 88.3% |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 69.2% | 49.4%† |
| LiveBench 1.0 Data Analysis | LiveBench | 68.0% | – |
| MMLU-Pro | Vals AI | 90.1% | 85.6%† |
| LegalBench | Vals AI | 87.3% | 83.8%† |
| CorpFin | Vals AI | – | 59.7%† |
| TaxEval | Vals AI | 74.7% | 74.6%† |
| MedQA | Vals AI | – | 96.1%† |
| PRBench Finance | Scale AI SEAL | – | 47.7% |
| PRBench Legal | Scale AI SEAL | – | 48.6% |
| MultiNRC | Scale AI SEAL | – | 45.5%† |
| MMLU-Pro (HELM) | HELM Capabilities | – | 85.9% |
| Excel Modeling Benchmark | Vals AI | 71.3% | – |
| MedCode | Vals AI | 53.4% | 47.3%† |
| MedScribe | Vals AI | 83.9% | 76.7%† |
| GDP.pdf | Epoch AI Benchmarking Hub | 23.8% | – |
| Instruction following | |||
| LiveBench Language | LiveBench | 85.5% | – |
| LiveBench Instruction Following | LiveBench | 79.9% | – |
| IFBench | Artificial Analysis | – | 71.4% |
| MultiChallenge | Scale AI SEAL | – | 56.6%† |
| TutorBench | Scale AI SEAL | – | 52.1%† |
| IFEval (HELM) | HELM Capabilities | – | 86.9% |
| WildBench (HELM) | HELM Capabilities | – | 86.1% |
| Arena Instruction Following | Arena (LMArena) | 1487 | 1403 |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1490 | 1432 |
| Arena Creative Writing | Arena (LMArena) | 1490 | 1383 |
| Arena Multi-turn | Arena (LMArena) | 1488 | 1420 |
| Arena Longer Queries | Arena (LMArena) | 1501 | 1411 |
| Lech Mazur Creative Writing | Lech Mazur | – | 83.9%† |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | 1314 | 1214 |
| MMMU-Pro | Artificial Analysis | 85.5% | 70.1% |
| VISTA | Scale AI SEAL | – | 50.1%† |
| MMMU (validation) | MMMU | – | 82.9% |
| MMMU-Pro (official) | MMMU | – | 76.4% |
| MMMU-Pro (Vals) | Vals AI | 89.0% | 80.4%† |
| MortgageTax | Vals AI | 66.7% | 65.7%† |
| VTB | Scale AI SEAL | – | 13.7% |
| GeoBench | GeoBench | – | 60.0%† |
| VPCT | Epoch AI Benchmarking Hub | – | 52.0%† |
| Long context | |||
| Fiction.LiveBench 120k | Fiction.live | – | 100.0%† |
| AA-LCR v1.1 | Artificial Analysis | 81.7% | 74.7% |
| MLCR | Artificial Analysis | 12.2% | – |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 158.2† | 146.9 |
| LiveBench 1.0 | LiveBench | 78.8% | – |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 39.1 | 20.2 |
| AA Progress Index v1 | Artificial Analysis | 317.4 | 258.3 |
| HELM Capabilities mean | HELM Capabilities | – | 81.1% |
| Vals RSI Index | Vals AI | 18.3% | – |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | – | 16.0% |
| MASK | Scale AI SEAL | – | 84.5%† |
| PropensityBench | Scale AI SEAL | – | 10.5% |
Data as of 2026-11-02. Best configuration of each model; every score links to its source on the model pages.
DuelLab GameBench 2, release gb2-20261026-cb69502a12d9 (https://benchmarks.duellab.org/releases/gb2-20261026-cb69502a12d9/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.
What changed
- Gemini 3.7 Flash (high): 1 new result (MirrorCode).
- Gemini 3.7 Flash (high): 1 new result (AA Progress Index v1).
- o3: 1 new result (AA Progress Index v1).
- Gemini 3.7 Flash (high): 2 new results (Harvey's Legal Agent Benchmark v1, Vals RSI Index).
- Gemini 3.7 Flash (high): input price moved from $0.38/M to $0.75/M (97% up); output price moved from $1.88/M to $3.75/M (99% up).
- Gemini 3.7 Flash (high): 1 score revision; input price moved from $0.75/M to $0.38/M (49% down); output price moved from $3.75/M to $1.88/M (50% down).
- Gemini 3.7 Flash (high): 1 new result (ForecastBench).
- o3: 1 score revision.
- Gemini 3.7 Flash (high): BenchLeader Index 60.8 → 62.6.
- Gemini 3.7 Flash (high): 18 new results (AA Intelligence Index v4.3.2, GPQA Diamond (AA), Humanity's Last Exam (AA)…).
Related comparisons
- Gemini 3.7 Flash vs Claude Opus 5.5
- Gemini 3.7 Flash vs Gemini 4 Carbon
- Gemini 3.7 Flash vs GPT-6 Astra
- o3 vs Claude Opus 5.5
- o3 vs Gemini 4 Carbon
- o3 vs GPT-6 Astra
- o3 vs GPT-6.1 Sol
- Gemini 3.6 Flash vs o3
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
Gemini 3.7 Flash vs o3: questions
- Is Gemini 3.7 Flash better than o3?
- Gemini 3.7 Flash (high) and o3 are neck and neck on quality (62.2 vs 61.0, within the ±5.0 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 2 Nov 2026, so check the category scores for your use.
- Gemini 3.7 Flash vs o3: which is cheaper, and will that change?
- Gemini 3.7 Flash is cheaper today: $1.50 against $3.50 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is Gemini 3.7 Flash or o3 better for coding?
- They are level in coding (63 vs 62 on the category index). On Arena Coding, the top shared coding benchmark, it is 1520 for Gemini 3.7 Flash against 1460 for o3.
- Which is faster, Gemini 3.7 Flash or o3?
- o3 streams ~1.5× faster (160 vs 91 output tokens per second, Artificial Analysis 7-day median).
- Is Gemini 3.7 Flash or o3 better for agents and tool use?
- o3 scores higher in agentic tasks (70 vs 48 on the category index, where 50 is average).
More questions (4)
- Which is better for long documents?
- Gemini 3.7 Flash scores higher on long-context benchmarks (66 vs 62). Gemini 3.7 Flash accepts more context: 1,048,576 against 200,000 tokens for o3.
- Which has lower latency?
- Gemini 3.7 Flash answers first: 2.4 s against 6.8 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 Gemini 3.7 Flash vs o3?
- Across the 15 benchmarks both have, Gemini 3.7 Flash leads 15, o3 leads 0. Every overall index that rates both puts Gemini 3.7 Flash ahead.
- When was Gemini 3.7 Flash released?
- Gemini 3.7 Flash was released on 13 Aug 2026.