Model comparison
DeepSeek-V3.2-Exp vs GPT-4o mini
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 25.5 on the Noometry Index.
Last verified . 28 shared benchmarks.
DeepSeekSummary
- They share 28 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 9 categories and GPT-4o mini 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 17.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 87.8% for DeepSeek-V3.2-Exp and 6.9% for GPT-4o mini.
- GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.26 / $0.38 for DeepSeek-V3.2-Exp.
- DeepSeek-V3.2-Exp accepts more context: 164K tokens versus 128K.
- DeepSeek-V3.2-Exp has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.2-Exp | GPT-4o mini | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 44.3 | 25.5 |
| Released | 2025-09-29 | 2024-07-18 |
| Weights | Open | Proprietary |
| Context window | 164K | 128K |
| Max output | 66K | 16K |
| Input $ / M tokens | $0.26 | $0.15 |
| Output $ / M tokens | $0.38 | $0.60 |
| Results tracked | 49 | 60 |
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), GPT-4o mini: 22.0 (#335)
| Benchmark | DeepSeek-V3.2-Exp | GPT-4o mini |
|---|---|---|
| Aider Polyglot | 74.2% | 3.6% |
| WeirdML | 39.5% | 11.8% |
| LMArena Coding | 1454 | 1290 |
| SWE-bench Verified (bash only) | 70% | — |
| LMArena WebDev | 1362 | — |
| SWE-bench Multilingual | 59% | — |
| SciCode | 38.9% | — |
| BigCodeBench Instruct | — | 46.1% |
| LiveBench Coding | — | 43.1% |
| BigCodeBench Complete | — | 57.4% |
| HumanEval+ | — | 83.5% |
| MBPP+ | — | 72.2% |
Agentic & Tool Use DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 32.7 (#59), GPT-4o mini: 27.5 (#101)
| Benchmark | DeepSeek-V3.2-Exp | GPT-4o mini |
|---|---|---|
| Terminal-Bench | 39.6% | — |
| APEX-Agents | 21.3% | — |
| Berkeley Function Calling Leaderboard | 56.7% | — |
| TheAgentCompany | 42.9% | — |
| BALROG | — | 17.4% |
| Vending-Bench 2 | 1,034 | — |
Reasoning DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 22.1 (#208), GPT-4o mini: 8.7 (#347)
| Benchmark | DeepSeek-V3.2-Exp | GPT-4o mini |
|---|---|---|
| ARC-AGI-2 | 4% | 0% |
| Kagi LLM Benchmark | 52.2% | 28.8% |
| Chess Puzzles | 14% | 0% |
| LMArena Hard Prompts | 1434 | 1267 |
| DTBench | 87.7% | 54.4% |
| LMCA | 29.1% | 10.4% |
| Epoch Capabilities Index | 146.27 | 126.56 |
| SimpleBench | — | 10.7% |
| NYT Connections (extended) | 36.7% | — |
| ARC-AGI-1 | 57% | — |
| CritPt | 2.9% | — |
| Thematic Generalization | 65% | — |
| LiveBench Reasoning | — | 32.8% |
| Mystery Game Puzzles | — | 12% |
| LiveBench Data Analysis | — | 50% |
| LiveBench | — | 41.3% |
| PIQA | — | 88.7% |
Math DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 41.7 (#87), GPT-4o mini: 10.4 (#314)
| Benchmark | DeepSeek-V3.2-Exp | GPT-4o mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 87.8% | 6.9% |
| LMArena Math | 1435 | 1267 |
| FrontierMath (Tiers 1-3) | — | 0.7% |
| MathArena Final-Answer Competitions | 57.7% | — |
| ProofBench | 8% | — |
| Omni-MATH | — | 28% |
| LiveBench Math | — | 36.3% |
| MATH Level 5 | — | 52.6% |
| FrontierMath (Feb 2025 set) | 22.1% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
| GSM8K | — | 91.3% |
Knowledge DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 51.7 (#66), GPT-4o mini: 17.7 (#284)
| Benchmark | DeepSeek-V3.2-Exp | GPT-4o mini |
|---|---|---|
| GPQA Diamond | 83.4% | 37.7% |
| LMArena Expert | 1436 | 1235 |
| SimpleQA Verified | — | 8.3% |
| MMLU-Pro | — | 60.3% |
| Confabulations | — | 37.2% |
| Vectara Hallucination Rate | 5.3% | — |
| GPQA (HELM) | — | 36.8% |
| BoolQ | — | 88.7% |
| MMLU | — | 81.8% |
Multimodal Not comparable
DeepSeek-V3.2-Exp: —, GPT-4o mini: 25.9 (#122)
| Benchmark | DeepSeek-V3.2-Exp | GPT-4o mini |
|---|---|---|
| LMArena Vision | — | 1066 |
| Video-MME | — | 64.8% |
| GeoBench | — | 64% |
| VPCT | — | 34% |
Multilingual DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 52.2 (#90), GPT-4o mini: 42.0 (#199)
| Benchmark | DeepSeek-V3.2-Exp | GPT-4o mini |
|---|---|---|
| LMArena Non-English | 1409 | 1266 |
| LMArena Chinese | 1461 | 1265 |
| LMArena French | 1433 | 1297 |
| LMArena German | 1440 | 1272 |
| LMArena Japanese | 1374 | 1216 |
| LMArena Korean | 1371 | 1195 |
| LMArena Russian | 1424 | 1275 |
| LMArena Spanish | 1440 | 1276 |
Instruction Following DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 74.5 (#93), GPT-4o mini: 61.9 (#239)
| Benchmark | DeepSeek-V3.2-Exp | GPT-4o mini |
|---|---|---|
| LMArena Instruction Following | 1413 | 1258 |
| LiveBench Instruction Following | — | 56.8% |
| IFEval | — | 78.2% |
Long Context DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 47.6 (#16), GPT-4o mini: 39.1 (#186)
| Benchmark | DeepSeek-V3.2-Exp | GPT-4o mini |
|---|---|---|
| LMArena Longer Query | 1428 | 1289 |
| 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), GPT-4o mini: 39.5 (#248)
| Benchmark | DeepSeek-V3.2-Exp | GPT-4o mini |
|---|---|---|
| LMArena Text | 1425 | 1286 |
| LMArena Creative Writing | 1403 | 1268 |
| EQ-Bench Creative Writing | 1515 | 873 |
| LMArena Multi-Turn | 1427 | 1285 |
| Short-Story Creative Writing | — | 67.2% |
| WildBench | — | 79.1% |
| LiveBench Language | — | 28.6% |
Frequently asked questions
Is DeepSeek-V3.2-Exp better than GPT-4o mini?
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 25.5 on the Noometry Index.
Which is cheaper, DeepSeek-V3.2-Exp or GPT-4o mini?
GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; DeepSeek-V3.2-Exp lists at $0.26 and $0.38.
Is DeepSeek-V3.2-Exp or GPT-4o mini better for coding?
DeepSeek-V3.2-Exp scores higher on coding benchmarks: 46.5 versus 22.0 in the Noometry coding category.
Which has the bigger context window?
DeepSeek-V3.2-Exp does, with 164K tokens against 128K.
How many benchmarks do DeepSeek-V3.2-Exp and GPT-4o mini share?
28 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 49 scored results on Noometry and GPT-4o mini has 60.