Model comparison
DeepSeek V4.1 Flash vs Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 52.8 on the Noometry Index. DeepSeek V4.1 Flash costs 17× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.
Last verified . 36 shared benchmarks.
DeepSeek
GoogleSummary
- They share 36 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 4 categories and Gemini 3.1 Pro Preview in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.1 Pro Preview leads 71.7 to 50.2.
- The biggest single-benchmark swing is ProofBench: 54% for DeepSeek V4.1 Flash and 26% for Gemini 3.1 Pro Preview.
- DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.
- Gemini 3.1 Pro Preview accepts more context: 1.05M tokens versus 1M.
- DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4.1 Flash | Gemini 3.1 Pro Preview | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 52.8 | 56.7 |
| Released | 2026-09-09 | 2026-02-19 |
| Weights | Open | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 393K | 66K |
| Input $ / M tokens | $0.15 | $2 |
| Output $ / M tokens | $0.60 | $12 |
| Results tracked | 37 | 71 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 52.9 (#32), Gemini 3.1 Pro Preview: 42.5 (#99)
| Benchmark | DeepSeek V4.1 Flash | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena WebDev | 1619 | 1447 |
| SciCode | 51.9% | 58.9% |
| LMArena Coding | 1506 | 1484 |
| ALE-Bench | 1,092 | 1,161 |
| SWE-bench Verified | — | 75.6% |
| DeepSWE | — | 11.7% |
| GSO | — | 22.6% |
| WeirdML | — | 72.1% |
| MirrorCode | — | 8.9% |
| AlgoTune | — | 2.02 |
Agentic & Tool Use Gemini 3.1 Pro Preview leads
DeepSeek V4.1 Flash: 31.2 (#69), Gemini 3.1 Pro Preview: 37.7 (#34)
| Benchmark | DeepSeek V4.1 Flash | Gemini 3.1 Pro Preview |
|---|---|---|
| APEX-Agents | 39.5% | 35.3% |
| GDP.pdf | 19.8% | 17% |
| Terminal-Bench | — | 80.2% |
| τ²-bench Banking | — | 26% |
| DeepResearch Bench | — | 47.8% |
| PostTrainBench | — | 22% |
| BALROG | — | 57% |
| ExploitBench | — | 26.1% |
| GBAEval | — | 0.8% |
| LMArena Search | — | 1211 |
| METR Time Horizons | — | 77% |
| Vending-Bench 2 | — | 3,774 |
Reasoning Gemini 3.1 Pro Preview leads
DeepSeek V4.1 Flash: 50.2 (#36), Gemini 3.1 Pro Preview: 71.7 (#12)
| Benchmark | DeepSeek V4.1 Flash | Gemini 3.1 Pro Preview |
|---|---|---|
| NYT Connections (extended) | 89.6% | 97.4% |
| CritPt | 14.3% | 17.7% |
| LMArena Hard Prompts | 1483 | 1485 |
| Mystery Game Puzzles | 43% | 34% |
| DTBench | 89.9% | 97.1% |
| LMCA | 47% | 53.8% |
| Epoch Capabilities Index | 154.9 | 154.77 |
| ARC-AGI-2 | — | 77.1% |
| SimpleBench | — | 79.6% |
| ARC-AGI-1 | — | 98% |
| Chess Puzzles | — | 55% |
| EnigmaEval | — | 36.8% |
| Thematic Generalization | — | 79.4% |
| EBR-Bench | — | 14.3% |
| Surface Evolver Bench | 46.3% | — |
| ForecastBench | — | 59 |
Math DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 66.7 (#25), Gemini 3.1 Pro Preview: 62.1 (#34)
| Benchmark | DeepSeek V4.1 Flash | Gemini 3.1 Pro Preview |
|---|---|---|
| FrontierMath (Tiers 1-3) | 67.4% | 59.6% |
| FrontierMath Tier 4 | 26.8% | 26.8% |
| OTIS Mock AIME 2024-2025 | 98.3% | 95.6% |
| ProofBench | 54% | 26% |
| LMArena Math | 1477 | 1485 |
| MathArena Final-Answer Competitions | — | 86.5% |
| FrontierMath (Feb 2025 set) | — | 36.9% |
| FrontierMath Tier 4 (v1) | — | 16.7% |
Knowledge Gemini 3.1 Pro Preview leads
DeepSeek V4.1 Flash: 57.9 (#38), Gemini 3.1 Pro Preview: 71.8 (#3)
| Benchmark | DeepSeek V4.1 Flash | Gemini 3.1 Pro Preview |
|---|---|---|
| GPQA Diamond | 89.8% | 94.4% |
| LMArena Expert | 1506 | 1485 |
| Humanity's Last Exam | — | 46.4% |
| SimpleQA Verified | — | 73.5% |
| Vectara Hallucination Rate | — | 10.4% |
Multimodal DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 39.1 (#61), Gemini 3.1 Pro Preview: 37.9 (#69)
| Benchmark | DeepSeek V4.1 Flash | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Vision | 1277 | 1296 |
| Furniture Assembly | 34.2% | 26.7% |
| Blueprint-Bench 2 | — | 26.5% |
| LMArena Document | — | 1444 |
Multilingual Gemini 3.1 Pro Preview leads
DeepSeek V4.1 Flash: 55.0 (#35), Gemini 3.1 Pro Preview: 57.0 (#12)
| Benchmark | DeepSeek V4.1 Flash | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Non-English | 1448 | 1477 |
| LMArena Chinese | 1497 | 1529 |
| LMArena French | 1452 | 1487 |
| LMArena German | 1484 | 1491 |
| LMArena Japanese | 1412 | 1493 |
| LMArena Korean | 1452 | 1455 |
| LMArena Russian | 1471 | 1498 |
| LMArena Spanish | 1459 | 1479 |
Instruction Following Too close to call
DeepSeek V4.1 Flash: 77.3 (#26), Gemini 3.1 Pro Preview: 77.0 (#32)
| Benchmark | DeepSeek V4.1 Flash | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Instruction Following | 1474 | 1466 |
Long Context Gemini 3.1 Pro Preview leads
DeepSeek V4.1 Flash: 45.2 (#47), Gemini 3.1 Pro Preview: 47.4 (#18)
| Benchmark | DeepSeek V4.1 Flash | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Longer Query | 1475 | 1483 |
| CL-bench | — | 20.8% |
| CL-bench Life | — | 16.9% |
Writing & Preference Too close to call
DeepSeek V4.1 Flash: 65.4 (#48), Gemini 3.1 Pro Preview: 66.1 (#37)
| Benchmark | DeepSeek V4.1 Flash | Gemini 3.1 Pro Preview |
|---|---|---|
| LMArena Text | 1462 | 1481 |
| LMArena Creative Writing | 1435 | 1482 |
| EQ-Bench Creative Writing | 1540 | 1491 |
| LMArena Multi-Turn | 1457 | 1488 |
| EQ-Bench 4 | — | 1142 |
Frequently asked questions
Is DeepSeek V4.1 Flash better than Gemini 3.1 Pro Preview?
Gemini 3.1 Pro Preview is the stronger model overall, scoring 56.7 to 52.8 on the Noometry Index. DeepSeek V4.1 Flash costs 17× less per token, which makes it the better buy when Gemini 3.1 Pro Preview's lead doesn't matter for your workload.
Which is cheaper, DeepSeek V4.1 Flash or Gemini 3.1 Pro Preview?
DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.
Is DeepSeek V4.1 Flash or Gemini 3.1 Pro Preview better for coding?
DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 42.5 in the Noometry coding category.
Which has the bigger context window?
Gemini 3.1 Pro Preview does, with 1.05M tokens against 1M.
How many benchmarks do DeepSeek V4.1 Flash and Gemini 3.1 Pro Preview share?
36 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and Gemini 3.1 Pro Preview has 71.