Model comparison
DeepSeek-V3.2-Exp vs Gemini 1.5 Pro (May 2024)
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 32.1 on the Noometry Index.
Last verified . 24 shared benchmarks.
DeepSeek
GoogleSummary
- They share 24 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 9 categories and Gemini 1.5 Pro (May 2024) in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-V3.2-Exp leads 51.7 to 29.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 87.8% for DeepSeek-V3.2-Exp and 23.1% for Gemini 1.5 Pro (May 2024).
- DeepSeek-V3.2-Exp has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.2-Exp | Gemini 1.5 Pro (May 2024) | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 44.3 | 32.1 |
| Released | 2025-09-29 | 2024-02-15 |
| Weights | Open | Proprietary |
| Context window | 164K | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.26 | — |
| Output $ / M tokens | $0.38 | — |
| Results tracked | 49 | 45 |
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 1.5 Pro (May 2024): 34.2 (#241)
| Benchmark | DeepSeek-V3.2-Exp | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| WeirdML | 39.5% | 22.2% |
| LMArena Coding | 1454 | 1294 |
| SWE-bench Verified (bash only) | 70% | — |
| Aider Polyglot | 74.2% | — |
| LMArena WebDev | 1362 | — |
| SWE-bench Multilingual | 59% | — |
| SciCode | 38.9% | — |
| BigCodeBench Instruct | — | 43.8% |
| BigCodeBench Complete | — | 57.5% |
| CadEval | — | 34% |
| HumanEval+ | — | 79.3% |
| MBPP+ | — | 74.6% |
Agentic & Tool Use DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 32.7 (#59), Gemini 1.5 Pro (May 2024): 17.9 (#145)
| Benchmark | DeepSeek-V3.2-Exp | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| TheAgentCompany | 42.9% | 3.4% |
| Terminal-Bench | 39.6% | — |
| APEX-Agents | 21.3% | — |
| Berkeley Function Calling Leaderboard | 56.7% | — |
| Cybench | — | 7.5% |
| BALROG | — | 21% |
| Vending-Bench 2 | 1,034 | — |
Reasoning DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 22.1 (#208), Gemini 1.5 Pro (May 2024): 12.3 (#338)
| Benchmark | DeepSeek-V3.2-Exp | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| ARC-AGI-2 | 4% | 0.8% |
| LMArena Hard Prompts | 1434 | 1296 |
| DTBench | 87.7% | 59% |
| Epoch Capabilities Index | 146.27 | 131.73 |
| SimpleBench | — | 27.1% |
| Kagi LLM Benchmark | 52.2% | — |
| NYT Connections (extended) | 36.7% | — |
| ARC-AGI-1 | 57% | — |
| CritPt | 2.9% | — |
| Chess Puzzles | 14% | — |
| Thematic Generalization | 65% | — |
| LMCA | 29.1% | — |
| BIG-Bench Hard | — | 89.2% |
| ForecastBench | — | 58.4 |
Math DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 41.7 (#87), Gemini 1.5 Pro (May 2024): 25.8 (#266)
| Benchmark | DeepSeek-V3.2-Exp | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 87.8% | 23.1% |
| LMArena Math | 1435 | 1315 |
| MathArena Final-Answer Competitions | 57.7% | — |
| ProofBench | 8% | — |
| Omni-MATH | — | 36.4% |
| MATH Level 5 | — | 70.4% |
| FrontierMath (Feb 2025 set) | 22.1% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 51.7 (#66), Gemini 1.5 Pro (May 2024): 29.4 (#239)
| Benchmark | DeepSeek-V3.2-Exp | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| GPQA Diamond | 83.4% | 57.2% |
| LMArena Expert | 1436 | 1279 |
| Humanity's Last Exam | — | 4.6% |
| MMLU-Pro | — | 73.7% |
| Confabulations | — | 13.5% |
| Vectara Hallucination Rate | 5.3% | — |
| GPQA (HELM) | — | 53.4% |
| MMLU | — | 86.9% |
Multimodal Not comparable
DeepSeek-V3.2-Exp: —, Gemini 1.5 Pro (May 2024): 36.8 (#77)
| Benchmark | DeepSeek-V3.2-Exp | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Vision | — | 1161 |
| Video-MME | — | 75% |
Multilingual DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 52.2 (#90), Gemini 1.5 Pro (May 2024): 45.3 (#174)
| Benchmark | DeepSeek-V3.2-Exp | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Non-English | 1409 | 1312 |
| LMArena Chinese | 1461 | 1331 |
| LMArena French | 1433 | 1302 |
| LMArena German | 1440 | 1286 |
| LMArena Japanese | 1374 | 1292 |
| LMArena Korean | 1371 | 1298 |
| LMArena Russian | 1424 | 1320 |
| LMArena Spanish | 1440 | 1311 |
Instruction Following DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 74.5 (#93), Gemini 1.5 Pro (May 2024): 68.6 (#185)
| Benchmark | DeepSeek-V3.2-Exp | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Instruction Following | 1413 | 1297 |
| IFEval | — | 83.7% |
Long Context DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 47.6 (#16), Gemini 1.5 Pro (May 2024): 39.8 (#169)
| Benchmark | DeepSeek-V3.2-Exp | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Longer Query | 1428 | 1308 |
| Fiction.LiveBench | 83.3% | — |
| CL-bench | 13.2% | — |
| CL-bench Life | 9.5% | — |
Writing & Preference DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 62.4 (#77), Gemini 1.5 Pro (May 2024): 52.4 (#172)
| Benchmark | DeepSeek-V3.2-Exp | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Text | 1425 | 1319 |
| LMArena Creative Writing | 1403 | 1333 |
| LMArena Multi-Turn | 1427 | 1296 |
| EQ-Bench Creative Writing | 1515 | — |
| WildBench | — | 81.3% |
Frequently asked questions
Is DeepSeek-V3.2-Exp better than Gemini 1.5 Pro (May 2024)?
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 32.1 on the Noometry Index.
Is DeepSeek-V3.2-Exp or Gemini 1.5 Pro (May 2024) better for coding?
DeepSeek-V3.2-Exp scores higher on coding benchmarks: 46.5 versus 34.2 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.2-Exp and Gemini 1.5 Pro (May 2024) share?
24 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 49 scored results on Noometry and Gemini 1.5 Pro (May 2024) has 45.