Model comparison
DeepSeek-V2.5 (Sep 2024) vs Gemini 2.5 Flash-Lite
DeepSeek-V2.5 (Sep 2024) and Gemini 2.5 Flash-Lite score almost the same on the Noometry Index (37.6 vs 37.0), so choose on price, context window or the category you care about most.
Last verified . 17 shared benchmarks.
DeepSeek
GoogleSummary
- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 3 categories and Gemini 2.5 Flash-Lite in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemini 2.5 Flash-Lite leads 56.8 to 49.8.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Gemini 2.5 Flash-Lite | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 37.6 | 37.0 |
| Released | 2024-09-06 | 2025-06-17 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.40 |
| Results tracked | 22 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.5 Flash-Lite leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Gemini 2.5 Flash-Lite: 38.5 (#173)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Coding | 1309 | 1373 |
| Aider Polyglot | 17.8% | — |
| WeirdML | — | 35.2% |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| ALE-Bench | — | 325.9 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Agentic & Tool Use Not comparable
DeepSeek-V2.5 (Sep 2024): —, Gemini 2.5 Flash-Lite: 28.0 (#96)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 2.5 Flash-Lite |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 36.9% |
Reasoning DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Gemini 2.5 Flash-Lite: 22.2 (#205)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1377 |
| Kagi LLM Benchmark | — | 40.5% |
| DTBench | — | 62.8% |
| LMCA | — | 18.1% |
| Epoch Capabilities Index | — | 133.94 |
Math Gemini 2.5 Flash-Lite leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Gemini 2.5 Flash-Lite: 38.0 (#144)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Math | 1288 | 1373 |
| Omni-MATH | — | 48% |
Knowledge DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Gemini 2.5 Flash-Lite: 32.5 (#210)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Expert | 1266 | 1373 |
| MMLU-Pro | — | 53.7% |
| Vectara Hallucination Rate | — | 3.3% |
| GPQA (HELM) | — | 30.9% |
Multimodal Not comparable
DeepSeek-V2.5 (Sep 2024): —, Gemini 2.5 Flash-Lite: 29.1 (#114)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Vision | — | 1198 |
| VPCT | — | 30% |
Multilingual Gemini 2.5 Flash-Lite leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Gemini 2.5 Flash-Lite: 49.3 (#134)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Non-English | 1273 | 1369 |
| LMArena Chinese | 1318 | 1404 |
| LMArena French | 1289 | 1388 |
| LMArena German | 1258 | 1389 |
| LMArena Japanese | 1228 | 1359 |
| LMArena Korean | 1209 | 1360 |
| LMArena Russian | 1289 | 1373 |
| LMArena Spanish | 1248 | 1396 |
Instruction Following Gemini 2.5 Flash-Lite leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Gemini 2.5 Flash-Lite: 70.0 (#168)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Instruction Following | 1280 | 1367 |
| IFEval | — | 81% |
Long Context DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Gemini 2.5 Flash-Lite: 33.3 (#262)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Longer Query | 1301 | 1373 |
| Fiction.LiveBench | — | 47.2% |
Writing & Preference Gemini 2.5 Flash-Lite leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Gemini 2.5 Flash-Lite: 56.8 (#135)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 2.5 Flash-Lite |
|---|---|---|
| LMArena Text | 1294 | 1379 |
| LMArena Creative Writing | 1285 | 1367 |
| LMArena Multi-Turn | 1297 | 1366 |
| WildBench | — | 81.8% |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Gemini 2.5 Flash-Lite?
DeepSeek-V2.5 (Sep 2024) and Gemini 2.5 Flash-Lite score almost the same on the Noometry Index (37.6 vs 37.0), so choose on price, context window or the category you care about most.
Is DeepSeek-V2.5 (Sep 2024) or Gemini 2.5 Flash-Lite better for coding?
Gemini 2.5 Flash-Lite scores higher on coding benchmarks: 38.5 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Gemini 2.5 Flash-Lite share?
17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Gemini 2.5 Flash-Lite has 33.