Model comparison
DeepSeek-V3.2-Exp vs Gemini 2.0 Flash (Feb 2025)
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 35.1 on the Noometry Index.
Last verified . 30 shared benchmarks.
DeepSeek
GoogleSummary
- They share 30 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 9 categories and Gemini 2.0 Flash (Feb 2025) in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-V3.2-Exp leads 51.7 to 32.0.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 70% for DeepSeek-V3.2-Exp and 13.5% for Gemini 2.0 Flash (Feb 2025).
- DeepSeek-V3.2-Exp has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.2-Exp | Gemini 2.0 Flash (Feb 2025) | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 44.3 | 35.1 |
| Released | 2025-09-29 | 2024-12-06 |
| Weights | Open | Proprietary |
| Context window | 164K | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.26 | — |
| Output $ / M tokens | $0.38 | — |
| Results tracked | 49 | 54 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 46.5 (#65), Gemini 2.0 Flash (Feb 2025): 28.4 (#315)
| Benchmark | DeepSeek-V3.2-Exp | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| SWE-bench Verified (bash only) | 70% | 13.5% |
| Aider Polyglot | 74.2% | 38.2% |
| WeirdML | 39.5% | 25.8% |
| LMArena Coding | 1454 | 1350 |
| LMArena WebDev | 1362 | — |
| SWE-bench Multilingual | 59% | — |
| SciCode | 38.9% | — |
| BigCodeBench Instruct | — | 45.9% |
| LiveBench Coding | — | 63.4% |
| BigCodeBench Complete | — | 59.9% |
| CadEval | — | 30% |
Agentic & Tool Use DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 32.7 (#59), Gemini 2.0 Flash (Feb 2025): 28.1 (#92)
| Benchmark | DeepSeek-V3.2-Exp | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| TheAgentCompany | 42.9% | 11.4% |
| Terminal-Bench | 39.6% | — |
| APEX-Agents | 21.3% | — |
| Berkeley Function Calling Leaderboard | 56.7% | — |
| Vending-Bench 2 | 1,034 | — |
Reasoning DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 22.1 (#208), Gemini 2.0 Flash (Feb 2025): 15.2 (#318)
| Benchmark | DeepSeek-V3.2-Exp | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| ARC-AGI-2 | 4% | 1.3% |
| Kagi LLM Benchmark | 52.2% | 37.8% |
| LMArena Hard Prompts | 1434 | 1346 |
| DTBench | 87.7% | 63.2% |
| Epoch Capabilities Index | 146.27 | 135.36 |
| SimpleBench | — | 31.1% |
| NYT Connections (extended) | 36.7% | — |
| ARC-AGI-1 | 57% | — |
| CritPt | 2.9% | — |
| Chess Puzzles | 14% | — |
| EnigmaEval | — | 1.1% |
| Thematic Generalization | 65% | — |
| LiveBench Reasoning | — | 78.2% |
| LiveBench Data Analysis | — | 69.4% |
| LMCA | 29.1% | — |
| LiveBench | — | 66.9% |
Math DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 41.7 (#87), Gemini 2.0 Flash (Feb 2025): 37.9 (#146)
| Benchmark | DeepSeek-V3.2-Exp | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 87.8% | 57.8% |
| LMArena Math | 1435 | 1352 |
| FrontierMath (Feb 2025 set) | 22.1% | 1.7% |
| MathArena Final-Answer Competitions | 57.7% | — |
| ProofBench | 8% | — |
| Omni-MATH | — | 45.9% |
| LiveBench Math | — | 75.8% |
| MATH Level 5 | — | 82.2% |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 51.7 (#66), Gemini 2.0 Flash (Feb 2025): 32.0 (#213)
| Benchmark | DeepSeek-V3.2-Exp | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| GPQA Diamond | 83.4% | 64.1% |
| LMArena Expert | 1436 | 1339 |
| Humanity's Last Exam | — | 6.6% |
| MMLU-Pro | — | 73.7% |
| Confabulations | — | 12.4% |
| Vectara Hallucination Rate | 5.3% | — |
| GPQA (HELM) | — | 55.6% |
| MMLU | — | 79.7% |
Multimodal Not comparable
DeepSeek-V3.2-Exp: —, Gemini 2.0 Flash (Feb 2025): 36.5 (#79)
| Benchmark | DeepSeek-V3.2-Exp | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Vision | — | 1158 |
| GeoBench | — | 77% |
Multilingual DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 52.2 (#90), Gemini 2.0 Flash (Feb 2025): 47.4 (#149)
| Benchmark | DeepSeek-V3.2-Exp | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Non-English | 1409 | 1342 |
| LMArena Chinese | 1461 | 1373 |
| LMArena French | 1433 | 1391 |
| LMArena German | 1440 | 1353 |
| LMArena Japanese | 1374 | 1294 |
| LMArena Korean | 1371 | 1313 |
| LMArena Russian | 1424 | 1351 |
| LMArena Spanish | 1440 | 1363 |
Instruction Following Too close to call
DeepSeek-V3.2-Exp: 74.5 (#93), Gemini 2.0 Flash (Feb 2025): 74.4 (#97)
| Benchmark | DeepSeek-V3.2-Exp | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Instruction Following | 1413 | 1336 |
| LiveBench Instruction Following | — | 85.8% |
| IFEval | — | 84.1% |
Long Context DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 47.6 (#16), Gemini 2.0 Flash (Feb 2025): 38.1 (#203)
| Benchmark | DeepSeek-V3.2-Exp | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| Fiction.LiveBench | 83.3% | 61.1% |
| LMArena Longer Query | 1428 | 1344 |
| CL-bench | 13.2% | — |
| CL-bench Life | 9.5% | — |
Writing & Preference DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 62.4 (#77), Gemini 2.0 Flash (Feb 2025): 49.5 (#190)
| Benchmark | DeepSeek-V3.2-Exp | Gemini 2.0 Flash (Feb 2025) |
|---|---|---|
| LMArena Text | 1425 | 1354 |
| LMArena Creative Writing | 1403 | 1340 |
| EQ-Bench Creative Writing | 1515 | 1128 |
| LMArena Multi-Turn | 1427 | 1350 |
| Short-Story Creative Writing | — | 73.8% |
| WildBench | — | 80% |
| LiveBench Language | — | 51.3% |
Frequently asked questions
Is DeepSeek-V3.2-Exp better than Gemini 2.0 Flash (Feb 2025)?
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 35.1 on the Noometry Index.
Is DeepSeek-V3.2-Exp or Gemini 2.0 Flash (Feb 2025) better for coding?
DeepSeek-V3.2-Exp scores higher on coding benchmarks: 46.5 versus 28.4 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.2-Exp and Gemini 2.0 Flash (Feb 2025) share?
30 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 49 scored results on Noometry and Gemini 2.0 Flash (Feb 2025) has 54.