Gemini 2.0 Flash Thinking Exp: benchmark scores, price and ranking
Gemini 2.0 Flash Thinking Exp from Google DeepMind,Google ranks #549 of 743 LLMs on the LLMs Tiger aggregate benchmark score (45.9), based on 6 benchmark results captured up to 2026-10-13.
- Organisation
- Google DeepMind,Google
- Type
- Preview release
- Open weights
- No
- Aggregate rank
- #549 of 743 (score 45.9)
Relative to other models, Gemini 2.0 Flash Thinking Exp is strongest on OTIS Mock AIME (#96 of 189) and weakest on SimpleBench (#43 of 61).
Across the 6 benchmarks where at least ten models are scored, Gemini 2.0 Flash Thinking Exp is in the top 10% on 0 and in the top half on 0.
Gemini 2.0 Flash Thinking Exp benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| OTIS Mock AIME | 57.8% | #96 of 189 | Epoch AI Benchmarking Hub | 2026-10-13 |
| GPQA Diamond | 57.1% | #171 of 275 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Humanity's Last Exam | 6.6% | #18 of 27 | Epoch AI Benchmarking Hub | 2026-10-13 |
| EnigmaEval | 1.1% | #16 of 24 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Fiction.liveBench | 52.8% | #32 of 47 | Epoch AI Benchmarking Hub | 2026-10-13 |
| SimpleBench | 30.7% | #43 of 61 | Epoch AI Benchmarking Hub | 2026-10-13 |
About Gemini 2.0 Flash Thinking Exp
Gemini 2.0 Flash Thinking Exp is a preview release from Google DeepMind,Google. No API price is listed for it yet. We hold 6 benchmark results for it across 2 areas, and none is in the top tenth of its board.
Where Gemini 2.0 Flash Thinking Exp stands
On our aggregate score, Gemini 2.0 Flash Thinking Exp is #549 of 743 ranked models, in the lower half. Its score is 45.9; the scale is centred on 50, so it sits 4.1 points below the typical model. That beats 26% of the ranked field. Among the 5 ranked Google DeepMind,Google models it is #5. The next one up is Gemini 2.0 Flash (Feb 2025) at 46.1.
Gemini 2.0 Flash Thinking Exp, benchmark by benchmark
Gemini 2.0 Flash Thinking Exp lands below the middle on OTIS Mock AIME: 57.8%, #96 of 189, with 50% of the field scoring higher. Claude Fable 5.1 (max) leads at 100.0%; the closest result above is Claude 3.7 Sonnet (64k thinking) at 57.8%. It covers competition maths (AIME 2024-25 style). The median score on this board is also 57.8%. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Gemini 2.0 Flash Thinking Exp lands below the middle on GPQA Diamond: 57.1%, #171 of 275, with 62% of the field scoring higher. GPT-6 Astra (max) leads at 95.8%; the closest result above is gemini-1.5-pro-002 at 57.2%. It covers expert-level science questions. The board median is 71.7%, so Gemini 2.0 Flash Thinking Exp is 14.6 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Gemini 2.0 Flash Thinking Exp lands below the middle on Humanity's Last Exam: 6.6%, #18 of 27, with 63% of the field scoring higher. Muse Spark leads at 40.6%; the closest result above is Claude Sonnet 4 (unknown thinking) at 7.8%. It covers expert-level questions across domains. The board median is 10.7%, so Gemini 2.0 Flash Thinking Exp is 4.2 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Gemini 2.0 Flash Thinking Exp lands below the middle on EnigmaEval: 1.1%, #16 of 24, with 62% of the field scoring higher. Gemini 3 Pro Preview leads at 18.2%; the closest result above is GPT-4.1 at 2.2%. It covers multi-step puzzle hunts. The board median is 2.9%, so Gemini 2.0 Flash Thinking Exp is 1.8 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Gemini 2.0 Flash Thinking Exp lands below the middle on Fiction.liveBench: 52.8%, #32 of 47, with 66% of the field scoring higher. grok-4-0709 leads at 94.4%; the closest result above is DeepSeek-V3.1 at 52.8%. It covers long-context story comprehension (16k). The board median is 61.1%, so Gemini 2.0 Flash Thinking Exp is 8.3 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Gemini 2.0 Flash Thinking Exp lands below the middle on SimpleBench: 30.7%, #43 of 61, with 69% of the field scoring higher. Claude Fable 5 (max) leads at 81.9%; the closest result above is DeepSeek-R1 at 30.9%. It covers trick questions that test common sense. The board median is 41.4%, so Gemini 2.0 Flash Thinking Exp is 10.7 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Strengths and weaknesses
Reasoning, maths and science: uneven, ahead of 37% of the field on average across 5 benchmarks. Its best board here is OTIS Mock AIME (#96 of 189) and its weakest is SimpleBench (#43 of 61).
Reading these numbers
The 6 scores on this page come from 1 source: Epoch AI Benchmarking Hub (6). No official leaderboard supplied any of them, so treat them as third-party measurements. With 6 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #546 DeepSeek-Coder-V2-Lite-Instruct (46.0)
- #547 o3-mini-2025-01-31 (low) (46.0)
- #548 nvidia.nemotron-nano-9b-v2 (46.0)
- #550 Mixtral-8x7B-v0.1 (45.9)
- #551 dbrx-instruct (45.9)
- #552 MAmmoTH2-7B-Plus (45.9)
More from Google DeepMind,Google
- gemini-exp-1206 (#176, 50.6)
- gemini-2.0-flash-02-05 (#365, 48.3)
- gemini-2.0-flash-exp (#431, 47.5)
- Gemini 2.0 Flash (Feb 2025) (#537, 46.1)
Compare it on the live leaderboard → · How the aggregate score works