Gemini 3 Flash: benchmark scores, price and ranking
Gemini 3 Flash from Google DeepMind ranks #120 of 743 LLMs on the LLMs Tiger aggregate benchmark score (51.5), based on 6 benchmark results captured up to 2026-10-13.
- Organisation
- Google DeepMind
- Type
- Fast / low-cost (flash) model
- Open weights
- No
- Released
- 2025-12-17 (source: curated)
- Cheapest API price
- $0.500 in / $3.00 out per million tokens (via aihubmix, observed 2026-10-13T20:47Z)
- Aggregate rank
- #120 of 743 (score 51.5)
Relative to other models, Gemini 3 Flash is strongest on Epoch ECI (#7 of 204) and weakest on LMArena Document Elo (#17 of 18).
Across the 6 benchmarks where at least ten models are scored, Gemini 3 Flash is in the top 10% on 3 and in the top half on 3.
Its cheapest listed input price, $0.500 per million tokens, is lower than that of 48% of the 427 models with a listed price.
Gemini 3 Flash benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| Epoch ECI | 152 | #7 of 204 | Epoch AI Benchmarking Hub | 2026-10-13 |
| SWE-bench Verified | 75.8% | #6 of 73 | SWE-bench Verified leaderboard | 2026-10-13 |
| SWE-bench Multilingual | 72.7% | #1 of 11 | SWE-bench Multilingual leaderboard | 2026-10-13 |
| LMArena Vision Elo | 1,273 | #14 of 22 | LMArena | 2026-10-05 |
| LMArena Text Elo | 1,473 | #23 of 28 | LMArena | 2026-10-05 |
| LMArena Document Elo | 1,413 | #17 of 18 | LMArena | 2026-10-13 |
About Gemini 3 Flash
Gemini 3 Flash is a smaller, lower-cost model from Google DeepMind. It was released on 2025-12-17, according to the developer's announcement. The cheapest API listing we track charges $0.500 per million input tokens and $3.00 per million output tokens, through aihubmix. We hold 6 benchmark results for it across 2 areas, and 3 are in the top tenth of their boards.
Where Gemini 3 Flash stands
On our aggregate score, Gemini 3 Flash is #120 of 743 ranked models, in the top quarter. Its score is 51.5; the scale is centred on 50, so it sits 1.5 points above the typical model. That beats 84% of the ranked field. Among the 41 ranked Google DeepMind models it is #6. The next one up is AI co-mathematician at 52.3. The next one down is Gemini 2.5 Pro Exp (Mar 2025) at 51.2.
Gemini 3 Flash, benchmark by benchmark
On Epoch ECI, Gemini 3 Flash scores 152 and ranks #7 of 204. Only 6 models score higher, led by Qwen 3.8 Max at 156, which is 5 points ahead. It covers Epoch Capabilities Index: Epoch's own aggregate of ~40 benchmarks. The board median is 127, so Gemini 3 Flash is 25 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
On SWE-bench Verified, Gemini 3 Flash scores 75.8% and ranks #6 of 73. Only 5 models score higher, led by Claude Opus 4.7 (max) at 83.5%, which is 7.7 points ahead. It covers real GitHub issues resolved. The board median is 56.4%, so Gemini 3 Flash is 19.4 points above it. Source: SWE-bench Verified leaderboard, captured 2026-10-13.
SWE-bench Multilingual is where Gemini 3 Flash does best: 72.7%, first of 11. The next result is Claude 4.6 Opus at 72.0%, 0.7 points behind. It covers real GitHub issues resolved. The board median is 68.3%, so Gemini 3 Flash is 4.4 points above it. Source: SWE-bench Multilingual leaderboard, captured 2026-10-13.
Gemini 3 Flash lands below the middle on LMArena Vision Elo: 1,273, #14 of 22, with 59% of the field scoring higher. Gemini 3.7 Flash (high) leads at 1,296; the closest result above is GPT-5.5 Instant at 1,276. It covers crowd-voted image understanding. The board median is 1,279, so Gemini 3 Flash is 6 points below it. Source: LMArena, captured 2026-10-05.
LMArena Text Elo is a weak spot. Gemini 3 Flash scores 1,473, #23 of 28, behind 79% of the models measured. The leader, gemini-4-argon-high, reaches 1,525. It covers head-to-head chat preference (crowd votes). The board median is 1,478, so Gemini 3 Flash is 4 points below it. Source: LMArena, captured 2026-10-05.
LMArena Document Elo is a weak spot. Gemini 3 Flash scores 1,413, #17 of 18, behind 89% of the models measured. The leader, Claude Fable 5.1 (max), reaches 1,513. It covers crowd-voted questions about documents. The board median is 1,440, so Gemini 3 Flash is 26 points below it. Source: LMArena, captured 2026-10-13.
Strengths and weaknesses
General knowledge and chat: uneven, ahead of 49% of the field on average across 5 benchmarks. Its best board here is Epoch ECI (#7 of 204) and its weakest is LMArena Document Elo (#17 of 18).
Price and value
The median input price across the 427 priced models is $0.500 per million tokens, so Gemini 3 Flash costs about the same as the typical listing. Models that score within 1.5 points or better and cost less: DeepSeek V4 Flash 0731 (max) ($0.016, 53.1), Qwen3.7 Flash ($0.030, 50.5), GLM-5.2 (high) ($0.060, 51.6). Similar scores cost more on Kimi K2 ($0.550) and MiniMax-M1-80k ($0.550).
Release history
The Google DeepMind model released before it was Gemini 3 Pro on 2025-11-18, which scores 50.6. The next one was Gemini 3 Deep Think on 2026-02-12, at 52.6.
Reading these numbers
The 6 scores on this page come from 4 sources: LMArena (3), Epoch AI Benchmarking Hub (1), SWE-bench Multilingual leaderboard (1), SWE-bench Verified leaderboard (1). 1 of them come from an official leaderboard and 5 from datasets or third-party runs. With 6 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #117 NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 (51.5)
- #118 GLM-5 (51.5)
- #119 GLM-5.1-MXFP4-Mixed-CT-AutoRound (51.5)
- #121 Claude Opus 4.6 (120K, High) (51.5)
- #122 Qwen3 235B A22B diff, no think, Alibaba API (51.5)
- #123 Darwin-31B-Opus (51.4)
More from Google DeepMind
- Gemini 3.8 Flash (high) (#26, 54.0)
- Gemini 3.7 Flash (high) (#27, 53.9)
- Gemini 3 Pro Preview (#31, 53.7)
- Gemini 3 Deep Think (#60, 52.6)
- AI co-mathematician (#69, 52.3)
- Gemini 2.5 Pro Exp (Mar 2025) (#140, 51.2)
Compare it on the live leaderboard → · How the aggregate score works