Model comparison
Gemini 2.5 Deep Think vs Gemini 3.8 Flash
Gemini 3.8 Flash has enough public results to be ranked (#13); Gemini 2.5 Deep Think does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
GoogleSide by side
| Gemini 2.5 Deep Think | Gemini 3.8 Flash | |
|---|---|---|
| Provider | ||
| Noometry Index | — | 59.5 |
| Released | 2025-08-01 | 2026-09-02 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.75 |
| Output $ / M tokens | — | $3.75 |
| Results tracked | 2 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Gemini 2.5 Deep Think: —, Gemini 3.8 Flash: 56.4 (#17)
| Benchmark | Gemini 2.5 Deep Think | Gemini 3.8 Flash |
|---|---|---|
| DeepSWE | — | 73.8% |
| FrontierCode | — | 41.2% |
| CursorBench | — | 39.6% |
| LMArena WebDev | — | 1581 |
| FrontierSWE | — | 19.6% |
| SciCode | — | 56.6% |
| LMArena Coding | — | 1512 |
| ALE-Bench | — | 1,270 |
Agentic & Tool Use Not comparable
Gemini 2.5 Deep Think: —, Gemini 3.8 Flash: 40.3 (#22)
| Benchmark | Gemini 2.5 Deep Think | Gemini 3.8 Flash |
|---|---|---|
| APEX-Agents | — | 64.3% |
| GDP.pdf | — | 23.4% |
| Vending-Bench 2 | — | 5,094 |
Reasoning Not comparable
Gemini 2.5 Deep Think: —, Gemini 3.8 Flash: 64.7 (#13)
| Benchmark | Gemini 2.5 Deep Think | Gemini 3.8 Flash |
|---|---|---|
| NYT Connections (extended) | — | 97.4% |
| CritPt | — | 18.3% |
| Chess Puzzles | — | 61% |
| LMArena Hard Prompts | — | 1506 |
| Mystery Game Puzzles | — | 47% |
| DTBench | — | 95.7% |
| LMCA | — | 52.9% |
| Surface Evolver Bench | — | 76.9% |
| Epoch Capabilities Index | — | 157.13 |
Math Not comparable
Gemini 2.5 Deep Think: —, Gemini 3.8 Flash: 65.2 (#22)
| Benchmark | Gemini 2.5 Deep Think | Gemini 3.8 Flash |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 68.4% |
| FrontierMath Tier 4 | — | 22% |
| OTIS Mock AIME 2024-2025 | — | 98.9% |
| ProofBench | — | 48% |
| LMArena Math | — | 1528 |
| FrontierMath (Feb 2025 set) | 29% | — |
| FrontierMath Tier 4 (v1) | 10.4% | — |
Knowledge Not comparable
Gemini 2.5 Deep Think: —, Gemini 3.8 Flash: 74.9 (#2)
| Benchmark | Gemini 2.5 Deep Think | Gemini 3.8 Flash |
|---|---|---|
| GPQA Diamond | — | 95.4% |
| Humanity's Last Exam | — | 44.5% |
| SimpleQA Verified | — | 69.7% |
| LMArena Expert | — | 1529 |
Multimodal Not comparable
Gemini 2.5 Deep Think: —, Gemini 3.8 Flash: 40.9 (#33)
| Benchmark | Gemini 2.5 Deep Think | Gemini 3.8 Flash |
|---|---|---|
| LMArena Vision | — | 1312 |
| Blueprint-Bench 2 | — | 38.6% |
| Furniture Assembly | — | 31.7% |
Multilingual Not comparable
Gemini 2.5 Deep Think: —, Gemini 3.8 Flash: 57.9 (#5)
| Benchmark | Gemini 2.5 Deep Think | Gemini 3.8 Flash |
|---|---|---|
| LMArena Non-English | — | 1486 |
| LMArena Chinese | — | 1547 |
| LMArena French | — | 1502 |
| LMArena German | — | 1470 |
| LMArena Japanese | — | 1505 |
| LMArena Korean | — | 1479 |
| LMArena Russian | — | 1507 |
| LMArena Spanish | — | 1492 |
Instruction Following Not comparable
Gemini 2.5 Deep Think: —, Gemini 3.8 Flash: 78.2 (#11)
| Benchmark | Gemini 2.5 Deep Think | Gemini 3.8 Flash |
|---|---|---|
| LMArena Instruction Following | — | 1489 |
Long Context Not comparable
Gemini 2.5 Deep Think: —, Gemini 3.8 Flash: 46.2 (#23)
| Benchmark | Gemini 2.5 Deep Think | Gemini 3.8 Flash |
|---|---|---|
| LMArena Longer Query | — | 1506 |
Writing & Preference Not comparable
Gemini 2.5 Deep Think: —, Gemini 3.8 Flash: 72.1 (#16)
| Benchmark | Gemini 2.5 Deep Think | Gemini 3.8 Flash |
|---|---|---|
| LMArena Text | — | 1494 |
| LMArena Creative Writing | — | 1485 |
| EQ-Bench Creative Writing | — | 1748 |
| LMArena Multi-Turn | — | 1503 |
Frequently asked questions
Is Gemini 2.5 Deep Think better than Gemini 3.8 Flash?
Gemini 3.8 Flash has enough public results to be ranked (#13); Gemini 2.5 Deep Think does not yet, so treat this comparison as directional.
How many benchmarks do Gemini 2.5 Deep Think and Gemini 3.8 Flash share?
0 benchmarks have published results for both models. Gemini 2.5 Deep Think has 2 scored results on Noometry and Gemini 3.8 Flash has 46.