Model comparison
DeepSeek-V2.5 (Sep 2024) vs Gemini 3.5 Flash Lite
Gemini 3.5 Flash Lite is the stronger model overall, scoring 41.5 to 37.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeek
GoogleSummary
- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 1 category and Gemini 3.5 Flash Lite in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemini 3.5 Flash Lite leads 50.1 to 34.8.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Gemini 3.5 Flash Lite | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 37.6 | 41.5 |
| Released | 2024-09-06 | 2026-07-21 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $2.50 |
| Results tracked | 22 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 3.5 Flash Lite leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Gemini 3.5 Flash Lite: 42.4 (#104)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 3.5 Flash Lite |
|---|---|---|
| LMArena Coding | 1309 | 1453 |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1440 |
| SciCode | — | 41.3% |
| WeirdML | — | 39% |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| ALE-Bench | — | 765.27 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Agentic & Tool Use Not comparable
DeepSeek-V2.5 (Sep 2024): —, Gemini 3.5 Flash Lite: 25.7 (#107)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 3.5 Flash Lite |
|---|---|---|
| APEX-Agents | — | 29.3% |
| GDP.pdf | — | 10% |
Reasoning Gemini 3.5 Flash Lite leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Gemini 3.5 Flash Lite: 27.8 (#114)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 3.5 Flash Lite |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1441 |
| ARC-AGI-2 | — | 10.3% |
| NYT Connections (extended) | — | 60.4% |
| ARC-AGI-1 | — | 53.5% |
| CritPt | — | 0% |
| Chess Puzzles | — | 22% |
| Mystery Game Puzzles | — | 19% |
| DTBench | — | 83.5% |
| LMCA | — | 37.6% |
| Epoch Capabilities Index | — | 145.13 |
Math DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Gemini 3.5 Flash Lite: 25.9 (#264)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 3.5 Flash Lite |
|---|---|---|
| LMArena Math | 1288 | 1433 |
| FrontierMath (Tiers 1-3) | — | 26% |
| FrontierMath Tier 4 | — | 0% |
| OTIS Mock AIME 2024-2025 | — | 71.1% |
| ProofBench | — | 13% |
Knowledge Gemini 3.5 Flash Lite leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Gemini 3.5 Flash Lite: 50.1 (#72)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 3.5 Flash Lite |
|---|---|---|
| LMArena Expert | 1266 | 1435 |
| GPQA Diamond | — | 83.3% |
Multimodal Not comparable
DeepSeek-V2.5 (Sep 2024): —, Gemini 3.5 Flash Lite: 41.1 (#40)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 3.5 Flash Lite |
|---|---|---|
| LMArena Vision | — | 1268 |
Multilingual Gemini 3.5 Flash Lite leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Gemini 3.5 Flash Lite: 53.5 (#63)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 3.5 Flash Lite |
|---|---|---|
| LMArena Non-English | 1273 | 1427 |
| LMArena Chinese | 1318 | 1469 |
| LMArena French | 1289 | 1451 |
| LMArena German | 1258 | 1454 |
| LMArena Japanese | 1228 | 1427 |
| LMArena Korean | 1209 | 1407 |
| LMArena Russian | 1289 | 1443 |
| LMArena Spanish | 1248 | 1442 |
Instruction Following Gemini 3.5 Flash Lite leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Gemini 3.5 Flash Lite: 74.8 (#85)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 3.5 Flash Lite |
|---|---|---|
| LMArena Instruction Following | 1280 | 1420 |
Long Context Gemini 3.5 Flash Lite leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Gemini 3.5 Flash Lite: 43.9 (#84)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 3.5 Flash Lite |
|---|---|---|
| LMArena Longer Query | 1301 | 1435 |
Writing & Preference Gemini 3.5 Flash Lite leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Gemini 3.5 Flash Lite: 64.2 (#57)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 3.5 Flash Lite |
|---|---|---|
| LMArena Text | 1294 | 1435 |
| LMArena Creative Writing | 1285 | 1420 |
| LMArena Multi-Turn | 1297 | 1445 |
| EQ-Bench Creative Writing | — | 1559 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Gemini 3.5 Flash Lite?
Gemini 3.5 Flash Lite is the stronger model overall, scoring 41.5 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Gemini 3.5 Flash Lite better for coding?
Gemini 3.5 Flash Lite scores higher on coding benchmarks: 42.4 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Gemini 3.5 Flash Lite share?
17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Gemini 3.5 Flash Lite has 39.