gemini-2.5-flash-lite-preview-06-17 (Default thinking length): benchmark scores, price and ranking
gemini-2.5-flash-lite-preview-06-17 (Default thinking length) from Google DeepMind ranks #627 of 743 LLMs on the LLMs Tiger aggregate benchmark score (44.6), based on 5 benchmark results captured up to 2026-10-13.
- Organisation
- Google DeepMind
- Type
- Preview release
- Open weights
- No
- Released
- 2025-06-17 (source: name)
- Aggregate rank
- #627 of 743 (score 44.6)
Relative to other models, gemini-2.5-flash-lite-preview-06-17 (Default thinking length) is strongest on DTBench (#89 of 146) and weakest on ALE-Bench (#70 of 79).
Across the 5 benchmarks where at least ten models are scored, gemini-2.5-flash-lite-preview-06-17 (Default thinking length) is in the top 10% on 0 and in the top half on 0.
gemini-2.5-flash-lite-preview-06-17 (Default thinking length) benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| DTBench | 62.8% | #89 of 146 | Epoch AI Benchmarking Hub | 2026-10-13 |
| LMCA | 18.1% | #77 of 108 | Epoch AI Benchmarking Hub | 2026-10-13 |
| WeirdML | 35.2% | #78 of 109 | Epoch AI Benchmarking Hub | 2026-10-13 |
| Fiction.liveBench | 47.2% | #36 of 47 | Epoch AI Benchmarking Hub | 2026-10-13 |
| ALE-Bench | 326 | #70 of 79 | Epoch AI Benchmarking Hub | 2026-10-13 |
About gemini-2.5-flash-lite-preview-06-17 (Default thinking length)
gemini-2.5-flash-lite-preview-06-17 (Default thinking length) is a preview release from Google DeepMind. It was released on 2025-06-17, according to the model's own name. No API price is listed for it yet. We hold 5 benchmark results for it across 3 areas, and none is in the top tenth of its board.
Where gemini-2.5-flash-lite-preview-06-17 (Default thinking length) stands
On our aggregate score, gemini-2.5-flash-lite-preview-06-17 (Default thinking length) is #627 of 743 ranked models, in the lower half. Its score is 44.6; the scale is centred on 50, so it sits 5.4 points below the typical model. That beats 16% of the ranked field. Among the 41 ranked Google DeepMind models it is #28. The next one up is Gemini 2.0 Flash at 44.6. The next one down is gemini-1.5-pro-001 at 44.0.
gemini-2.5-flash-lite-preview-06-17 (Default thinking length), benchmark by benchmark
gemini-2.5-flash-lite-preview-06-17 (Default thinking length) lands below the middle on DTBench: 62.8%, #89 of 146, with 60% of the field scoring higher. Claude Opus 5.5 (max) leads at 98.9%; the closest result above is qwen2.5-72b-instruct at 62.9%. It covers dynamic tool-use benchmark. The board median is 68.8%, so gemini-2.5-flash-lite-preview-06-17 (Default thinking length) is 6.0 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
gemini-2.5-flash-lite-preview-06-17 (Default thinking length) lands below the middle on LMCA: 18.1%, #77 of 108, with 70% of the field scoring higher. Claude Opus 5.5 (max) leads at 68.2%; the closest result above is qwen3-14b at 18.2%. It covers language-model capability assessment. The board median is 29.2%, so gemini-2.5-flash-lite-preview-06-17 (Default thinking length) is 11.2 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
gemini-2.5-flash-lite-preview-06-17 (Default thinking length) lands below the middle on WeirdML: 35.2%, #78 of 109, with 71% of the field scoring higher. GPT-6 Astra (max) leads at 93.3%; the closest result above is DeepSeek-V3 (Mar 2025) at 36.1%. It covers unusual machine-learning tasks. The board median is 41.2%, so gemini-2.5-flash-lite-preview-06-17 (Default thinking length) is 6.0 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
gemini-2.5-flash-lite-preview-06-17 (Default thinking length) lands below the middle on Fiction.liveBench: 47.2%, #36 of 47, with 74% of the field scoring higher. grok-4-0709 leads at 94.4%; the closest result above is Gemini 2.5 Flash Preview (Apr 2025) at 47.2%. It covers long-context story comprehension (16k). The board median is 61.1%, so gemini-2.5-flash-lite-preview-06-17 (Default thinking length) is 13.9 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
ALE-Bench is a weak spot. gemini-2.5-flash-lite-preview-06-17 (Default thinking length) scores 326, #70 of 79, behind 87% of the models measured. The leader, GPT-6 Astra (max), reaches 2,951. It covers AtCoder heuristic-optimisation contests (performance rating). The board median is 764, so gemini-2.5-flash-lite-preview-06-17 (Default thinking length) is 438 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Strengths and weaknesses
General knowledge and chat: weak, ahead of 27% of the field on average across 3 benchmarks. Its best board here is LMCA (#77 of 108) and its weakest is Fiction.liveBench (#36 of 47).
Release history
The Google DeepMind model released before it was gemini-2.5-flash-lite-preview-06-17_16K on 2025-06-17, which scores 48.7. The next one was gemini-2.5-pro_16K on 2025-06-17, at 50.4.
Reading these numbers
The 5 scores on this page come from 1 source: Epoch AI Benchmarking Hub (5). No official leaderboard supplied any of them, so treat them as third-party measurements. With 5 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #624 Qwen2.5-1.5B (44.7)
- #625 Solar Pro 3 (44.7)
- #626 Gemini 2.0 Flash (44.6)
- #628 DeepSeek-R1-Distill-Qwen-1.5B (44.6)
- #629 granite-3.0-8b-base (44.6)
- #630 Mistral-7B-Instruct-v0.2 (44.6)
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 3 Flash (#120, 51.5)
Compare it on the live leaderboard → · How the aggregate score works