GoogleGemini 2.0 Flash Thinking
Gemini 2.0 Flash Thinking is a Google proprietary reasoning model, released 19 Dec 2024. Its best configuration (thinking reasoning effort) ranks #526 of 785 on the BenchLeader Index at 44.9 ±5.1, in the lower half. The ± is the point: 320 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in multimodal (56) and lowest in coding (32). Last measured 1 Sept 2026.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- 2M
- Full answer
- –
- Cost per run
- –
- Released
- 19 Dec 2024
- Overall index45
- Reasoning38
- Coding32
- Maths49
- Knowledge51
- Multimodal56
- Long context37
- Composite40
How its index has moved
8 Sept 2026 to 15 Oct 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | thinking | Source | Trend |
|---|---|---|---|
| GPQA Diamond | 57.1%#197 | Epoch AI Benchmarking Hub | |
| Humanity's Last Exam | 6.6%#39 | Scale AI / CAIS | |
| SimpleBench | 30.7%#69 | SimpleBench | |
| GPQA Diamond (AA)not in index | 70.1%#295 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 6.3%#396 | Artificial Analysis |
Coding
| Benchmark | thinking | Source | Trend |
|---|---|---|---|
| Aider Polyglot | 18.2%#40 | Aider polyglot leaderboard |
Maths
| Benchmark | thinking | Source | Trend |
|---|---|---|---|
| OTIS Mock AIME | 57.8%#167 | Epoch AI Benchmarking Hub | |
| MATH 500not in index | 84.6%#34 | Vals AI |
Human preference
| Benchmark | thinking | Source | Trend |
|---|---|---|---|
| Lech Mazur Creative Writingnot in index | 73.8%#27 | Lech Mazur |
Multimodal
| Benchmark | thinking | Source | Trend |
|---|---|---|---|
| VISTA | 45.5%#23 | Scale AI SEAL |
Long context
| Benchmark | thinking | Source | Trend |
|---|---|---|---|
| Fiction.LiveBench 120k | 37.5%#26 | Fiction.live |
Composite
| Benchmark | thinking | Source | Trend |
|---|---|---|---|
| Epoch Capabilities Indexnot in index | 135.2#132 | Epoch AI Benchmarking Hub | |
| AA Intelligence Index v4.3.2 | 9.4#400 | Artificial Analysis |
Safety & honesty
| Benchmark | thinking | Source | Trend |
|---|---|---|---|
| MASKnot in index | 49.5%#52 | Scale AI SEAL |
More from Google
See also
Questions people ask
- What are Gemini 2.0 Flash Thinking's benchmark scores?
- As of 25 Oct 2026, Gemini 2.0 Flash Thinking (thinking effort) scores 44.9 ±5.1 on the BenchLeader Index, strongest in multimodal (56) and weakest in coding (32). That rests on 9 independent benchmark results, and every score on this page links to its publisher.
- How does Gemini 2.0 Flash Thinking rank?
- Gemini 2.0 Flash Thinking (thinking effort) is #526 of 785 ranked configurations on 25 Oct 2026. 320 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- When was Gemini 2.0 Flash Thinking released?
- Google released Gemini 2.0 Flash Thinking on 19 Dec 2024.
Data as of 25 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Gemini 2.0 Flash Thinking: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/gemini-2-0-flash-thinking.