AI Rankings
Gemini 3.7 Flash vs GPT-6.1 Sol: Scores, Price and Which to Choose
Data updated
Read the model pages for the full picture: Gemini 3.7 Flash and GPT-6.1 Sol.
Side by side
- Gemini 3.7 Flash
- GPT-6.1 Sol
- Epoch Capabilities IndexGPT-6.1 Sol leads
Combined score over many tests. Bar shows where it sits between the lowest and highest score we track.
Gemini 3.7 Flash:158.0GPT-6.1 Sol:Better: 168.4 - Arena text ratingToo close to call
Rating from head-to-head votes by people. Bar shows where it sits between the lowest and highest score we track.
Gemini 3.7 Flash:1490GPT-6.1 Sol:1480 - Arena coding ratingToo close to call
Rating from head-to-head votes by people. Bar shows where it sits between the lowest and highest score we track.
Gemini 3.7 Flash:1520GPT-6.1 Sol:1537 - Arena web development ratingGPT-6.1 Sol leads
Rating from head-to-head votes by people. Bar shows where it sits between the lowest and highest score we track.
Gemini 3.7 Flash:1590GPT-6.1 Sol:Better: 1749 - Arena vision ratingToo close to call
Rating from head-to-head votes by people. Bar shows where it sits between the lowest and highest score we track.
Gemini 3.7 Flash:1295GPT-6.1 Sol:1294 - ARC-AGI-2GPT-6.1 Sol leads
Visual puzzles where the AI must work out a new rule from a few examples and apply it.
Gemini 3.7 Flash:84.6%GPT-6.1 Sol:Better: 94.2% - FrontierMath (Tiers 1-3)GPT-6.1 Sol leads
Original, very hard maths problems written by mathematicians.
Gemini 3.7 Flash:71.6%GPT-6.1 Sol:Better: 93.7% - GPQA DiamondToo close to call
Very hard multiple-choice science questions in biology, physics and chemistry, written by experts and designed so a quick web search does not give the answer.
Gemini 3.7 Flash:94.8%GPT-6.1 Sol:95.4% - OTIS Mock AIMEGPT-6.1 Sol leads
Maths competition problems in the style of the US AIME exam, from the 2024 and 2025 sets.
Gemini 3.7 Flash:97.2%GPT-6.1 Sol:Better: 100.0% - SimpleQA VerifiedGPT-6.1 Sol leads
Short factual questions that each have one correct answer.
Gemini 3.7 Flash:69.2%GPT-6.1 Sol:Better: 73.9% - Blended price per million tokensGemini 3.7 Flash costs less
Blended price: lower is better.
Gemini 3.7 Flash:Better: $1.50GPT-6.1 Sol:$4.00 - Context windowGemini 3.7 Flash leads
How much text it can read at once.
Gemini 3.7 Flash:Better: 1M tokensGPT-6.1 Sol:922K tokens
The numbers
| Measure | Gemini 3.7 Flash | GPT-6.1 Sol |
|---|---|---|
| Epoch Capabilities Index | 158.0 | 168.4 |
| Arena text ratingToo close to call | 1490 | 1480 |
| Arena coding ratingToo close to call | 1520 | 1537 |
| Arena web development rating | 1590 | 1749 |
| Arena vision ratingToo close to call | 1295 | 1294 |
| ARC-AGI-2 | 84.6% | 94.2% |
| FrontierMath (Tiers 1-3) | 71.6% | 93.7% |
| GPQA DiamondToo close to call | 94.8% | 95.4% |
| OTIS Mock AIME | 97.2% | 100.0% |
| SimpleQA Verified | 69.2% | 73.9% |
| Blended price per million tokens | $1.50 | $4.00 |
| Context window | 1M tokens | 922K tokens |
What it costs in everyday terms
- 100 chats with Gemini 3.7 Flash
- $0.26
- Blended price $1.50 per million tokens.
- 100 chats with GPT-6.1 Sol
- $0.70
- Blended price $4.00 per million tokens.
Who should pick which
Pick Gemini 3.7 Flash if these matter most
- Blended price per million tokens: $1.50 against $4.00
- Context window: 1M tokens against 922K tokens
Pick GPT-6.1 Sol if these matter most
- Epoch Capabilities Index: 168.4 against 158.0
- Arena web development rating: 1749 against 1590
- ARC-AGI-2: 94.2% against 84.6%
- FrontierMath (Tiers 1-3): 93.7% against 71.6%
- OTIS Mock AIME: 100.0% against 97.2%
- SimpleQA Verified: 73.9% against 69.2%
Too close to call: Arena text rating, Arena coding rating, Arena vision rating, GPQA Diamond.
Scores come from tests and votes, not from your own work. Try both on a task you care about before you commit.
Questions about this comparison
- Which is better, Gemini 3.7 Flash or GPT-6.1 Sol?
- GPT-6.1 Sol scores higher on 6 of 10 shared quality measures, Gemini 3.7 Flash on 0. 4 measures are too close to call. Gemini 3.7 Flash costs about 63% less than GPT-6.1 Sol on a blended price of $1.50 against $4.00 per million tokens. Which one is better for you depends on your task and budget, so test both on your own work.
- Which is cheaper, Gemini 3.7 Flash or GPT-6.1 Sol?
- Gemini 3.7 Flash is cheaper on blended price: $1.50 per million tokens for Gemini 3.7 Flash against $4.00 for GPT-6.1 Sol. For 100 chats of about 1,000 tokens in and 500 tokens back, that is about $0.26 for Gemini 3.7 Flash and $0.70 for GPT-6.1 Sol.
- Which is better for coding, Gemini 3.7 Flash or GPT-6.1 Sol?
- On Arena coding rating they are too close to call (1520 and 1537).
Where this data comes from
- Epoch AI: Benchmark data: Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks (CC BY 4.0). We match models across sources, rank them and show them in charts. Scores are not changed. Epoch AI does not endorse this site.
- Arena (formerly LMArena): Human-preference ratings: Arena (arena.ai) leaderboard dataset, CC BY 4.0. We keep the latest published ratings, match them to models from other sources and rank them. Ratings are not changed. Arena does not endorse this site.
- LiteLLM model price list: Prices and context windows: LiteLLM model price list (github.com/BerriAI/litellm, MIT licence). We use the model maker's own price entry when there is one. Prices change often, so always confirm on the maker's site before you buy.
Newest data on this page: 26 Oct 2026. Prices are list prices and change often, so confirm on the maker's site before you buy. Sponsors never change a score or an order. How we calculate this · Report a mistake