Model comparison
DeepSeek-V3.2-Exp vs Gemini 4 Argon
Gemini 4 Argon is the stronger model overall, scoring 56.5 to 44.3 on the Noometry Index.
Last verified . 19 shared benchmarks.
DeepSeek
GoogleSummary
- They share 19 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 1 category and Gemini 4 Argon in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemini 4 Argon leads 73.9 to 41.7.
- The biggest single-benchmark swing is ProofBench: 8% for DeepSeek-V3.2-Exp and 99% for Gemini 4 Argon.
- DeepSeek-V3.2-Exp has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.2-Exp | Gemini 4 Argon | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 44.3 | 56.5 |
| Released | 2025-09-29 | 2026-09-30 |
| Weights | Open | Proprietary |
| Context window | 164K | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.26 | — |
| Output $ / M tokens | $0.38 | — |
| Results tracked | 49 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemini 4 Argon leads
DeepSeek-V3.2-Exp: 46.5 (#65), Gemini 4 Argon: 62.0 (#9)
| Benchmark | DeepSeek-V3.2-Exp | Gemini 4 Argon |
|---|---|---|
| LMArena WebDev | 1362 | 1678 |
| SciCode | 38.9% | 61.8% |
| LMArena Coding | 1454 | 1550 |
| SWE-bench Verified (bash only) | 70% | — |
| Aider Polyglot | 74.2% | — |
| SWE-bench Multilingual | 59% | — |
| FrontierSWE | — | 55% |
| WeirdML | 39.5% | — |
Agentic & Tool Use Gemini 4 Argon leads
DeepSeek-V3.2-Exp: 32.7 (#59), Gemini 4 Argon: 49.2 (#8)
| Benchmark | DeepSeek-V3.2-Exp | Gemini 4 Argon |
|---|---|---|
| APEX-Agents | 21.3% | 82.2% |
| Vending-Bench 2 | 1,034 | 13,718 |
| Terminal-Bench | 39.6% | — |
| Berkeley Function Calling Leaderboard | 56.7% | — |
| TheAgentCompany | 42.9% | — |
Reasoning Gemini 4 Argon leads
DeepSeek-V3.2-Exp: 22.1 (#208), Gemini 4 Argon: 44.2 (#47)
| Benchmark | DeepSeek-V3.2-Exp | Gemini 4 Argon |
|---|---|---|
| CritPt | 2.9% | 27.1% |
| LMArena Hard Prompts | 1434 | 1548 |
| ARC-AGI-2 | 4% | — |
| Kagi LLM Benchmark | 52.2% | — |
| NYT Connections (extended) | 36.7% | — |
| ARC-AGI-1 | 57% | — |
| Chess Puzzles | 14% | — |
| Thematic Generalization | 65% | — |
| DTBench | 87.7% | — |
| LMCA | 29.1% | — |
| Epoch Capabilities Index | 146.27 | — |
Math Gemini 4 Argon leads
DeepSeek-V3.2-Exp: 41.7 (#87), Gemini 4 Argon: 73.9 (#17)
| Benchmark | DeepSeek-V3.2-Exp | Gemini 4 Argon |
|---|---|---|
| ProofBench | 8% | 99% |
| LMArena Math | 1435 | 1536 |
| MathArena Final-Answer Competitions | 57.7% | — |
| OTIS Mock AIME 2024-2025 | 87.8% | — |
| 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 4 Argon: 43.9 (#89)
| Benchmark | DeepSeek-V3.2-Exp | Gemini 4 Argon |
|---|---|---|
| LMArena Expert | 1436 | 1553 |
| GPQA Diamond | 83.4% | — |
| Vectara Hallucination Rate | 5.3% | — |
Multimodal Not comparable
DeepSeek-V3.2-Exp: —, Gemini 4 Argon: 46.5 (#14)
| Benchmark | DeepSeek-V3.2-Exp | Gemini 4 Argon |
|---|---|---|
| Blueprint-Bench 2 | — | 54.4% |
Multilingual Gemini 4 Argon leads
DeepSeek-V3.2-Exp: 52.2 (#90), Gemini 4 Argon: 60.3 (#1)
| Benchmark | DeepSeek-V3.2-Exp | Gemini 4 Argon |
|---|---|---|
| LMArena Non-English | 1409 | 1523 |
| LMArena Chinese | 1461 | 1610 |
| LMArena Russian | 1424 | 1537 |
| LMArena Spanish | 1440 | 1497 |
| LMArena French | 1433 | — |
| LMArena German | 1440 | — |
| LMArena Japanese | 1374 | — |
| LMArena Korean | 1371 | — |
Instruction Following Gemini 4 Argon leads
DeepSeek-V3.2-Exp: 74.5 (#93), Gemini 4 Argon: 80.1 (#2)
| Benchmark | DeepSeek-V3.2-Exp | Gemini 4 Argon |
|---|---|---|
| LMArena Instruction Following | 1413 | 1538 |
Long Context Too close to call
DeepSeek-V3.2-Exp: 47.6 (#16), Gemini 4 Argon: 47.6 (#15)
| Benchmark | DeepSeek-V3.2-Exp | Gemini 4 Argon |
|---|---|---|
| LMArena Longer Query | 1428 | 1549 |
| Fiction.LiveBench | 83.3% | — |
| CL-bench | 13.2% | — |
| CL-bench Life | 9.5% | — |
Writing & Preference Gemini 4 Argon leads
DeepSeek-V3.2-Exp: 62.4 (#77), Gemini 4 Argon: 71.4 (#19)
| Benchmark | DeepSeek-V3.2-Exp | Gemini 4 Argon |
|---|---|---|
| LMArena Text | 1425 | 1534 |
| LMArena Creative Writing | 1403 | 1531 |
| LMArena Multi-Turn | 1427 | 1557 |
| EQ-Bench Creative Writing | 1515 | — |
Frequently asked questions
Is DeepSeek-V3.2-Exp better than Gemini 4 Argon?
Gemini 4 Argon is the stronger model overall, scoring 56.5 to 44.3 on the Noometry Index.
Is DeepSeek-V3.2-Exp or Gemini 4 Argon better for coding?
Gemini 4 Argon scores higher on coding benchmarks: 62.0 versus 46.5 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.2-Exp and Gemini 4 Argon share?
19 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 49 scored results on Noometry and Gemini 4 Argon has 21.