Model comparison
DeepSeek-V2.5 (Sep 2024) vs Gemini 2.5 Flash
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 37.6 on the Noometry Index.
Last verified . 18 shared benchmarks.
DeepSeek
GoogleSummary
- They share 18 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 1 category and Gemini 2.5 Flash in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Gemini 2.5 Flash leads 52.3 to 42.5.
- The biggest single-benchmark swing is Aider Polyglot: 17.8% for DeepSeek-V2.5 (Sep 2024) and 55.1% for Gemini 2.5 Flash.
- 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 | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 37.6 | 39.3 |
| Released | 2024-09-06 | 2025-04-17 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $2.50 |
| Results tracked | 22 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 2.5 Flash leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Gemini 2.5 Flash: 35.8 (#220)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 2.5 Flash |
|---|---|---|
| Aider Polyglot | 17.8% | 55.1% |
| LMArena Coding | 1309 | 1424 |
| SWE-bench Verified (bash only) | — | 28.7% |
| WeirdML | — | 41.9% |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| ALE-Bench | — | 661.88 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Agentic & Tool Use Not comparable
DeepSeek-V2.5 (Sep 2024): —, Gemini 2.5 Flash: 30.8 (#74)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 2.5 Flash |
|---|---|---|
| Terminal-Bench | — | 17.1% |
| Berkeley Function Calling Leaderboard | — | 56.2% |
| TheAgentCompany | — | 41.1% |
| BALROG | — | 33.5% |
| Vending-Bench 2 | — | 548.84 |
Reasoning DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Gemini 2.5 Flash: 18.1 (#286)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 2.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1422 |
| ARC-AGI-2 | — | 2.5% |
| SimpleBench | — | 41.2% |
| Kagi LLM Benchmark | — | 56.8% |
| ARC-AGI-1 | — | 33.3% |
| CritPt | — | 1.1% |
| EnigmaEval | — | 2.7% |
| DTBench | — | 76.5% |
| LMCA | — | 27.5% |
| Epoch Capabilities Index | — | 143.03 |
| ForecastBench | — | 60.6 |
Math Gemini 2.5 Flash leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Gemini 2.5 Flash: 39.9 (#98)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 2.5 Flash |
|---|---|---|
| LMArena Math | 1288 | 1415 |
| OTIS Mock AIME 2024-2025 | — | 73.1% |
| Omni-MATH | — | 38.5% |
| FrontierMath (Feb 2025 set) | — | 4.8% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Gemini 2.5 Flash leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Gemini 2.5 Flash: 36.4 (#168)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 2.5 Flash |
|---|---|---|
| LMArena Expert | 1266 | 1426 |
| Humanity's Last Exam | — | 12.1% |
| MMLU-Pro | — | 63.9% |
| Confabulations | — | 16.8% |
| Vectara Hallucination Rate | — | 7.8% |
| GPQA (HELM) | — | 39% |
Multimodal Not comparable
DeepSeek-V2.5 (Sep 2024): —, Gemini 2.5 Flash: 41.8 (#32)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 2.5 Flash |
|---|---|---|
| LMArena Vision | — | 1253 |
| GeoBench | — | 76% |
| VPCT | — | 46.2% |
| SpatialViz-Bench | — | 36.9% |
Multilingual Gemini 2.5 Flash leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Gemini 2.5 Flash: 52.3 (#88)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 2.5 Flash |
|---|---|---|
| LMArena Non-English | 1273 | 1409 |
| LMArena Chinese | 1318 | 1450 |
| LMArena French | 1289 | 1433 |
| LMArena German | 1258 | 1418 |
| LMArena Japanese | 1228 | 1405 |
| LMArena Korean | 1209 | 1385 |
| LMArena Russian | 1289 | 1415 |
| LMArena Spanish | 1248 | 1421 |
Instruction Following Gemini 2.5 Flash leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Gemini 2.5 Flash: 75.7 (#54)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 2.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1280 | 1405 |
| IFEval | — | 89.8% |
Long Context Gemini 2.5 Flash leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Gemini 2.5 Flash: 47.5 (#17)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 2.5 Flash |
|---|---|---|
| LMArena Longer Query | 1301 | 1419 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference Gemini 2.5 Flash leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Gemini 2.5 Flash: 53.8 (#157)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Gemini 2.5 Flash |
|---|---|---|
| LMArena Text | 1294 | 1417 |
| LMArena Creative Writing | 1285 | 1400 |
| LMArena Multi-Turn | 1297 | 1408 |
| Short-Story Creative Writing | — | 76.5% |
| EQ-Bench Creative Writing | — | 1137 |
| WildBench | — | 81.7% |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Gemini 2.5 Flash?
Gemini 2.5 Flash is the stronger model overall, scoring 39.3 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Gemini 2.5 Flash better for coding?
Gemini 2.5 Flash scores higher on coding benchmarks: 35.8 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Gemini 2.5 Flash share?
18 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Gemini 2.5 Flash has 54.