Model comparison
DeepSeek V4.1 Flash vs Gemini 1.5 Pro (May 2024)
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 32.1 on the Noometry Index.
Last verified . 22 shared benchmarks.
DeepSeek
GoogleSummary
- They share 22 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 10 categories and Gemini 1.5 Pro (May 2024) in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4.1 Flash leads 66.7 to 25.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.3% for DeepSeek V4.1 Flash and 23.1% for Gemini 1.5 Pro (May 2024).
- DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4.1 Flash | Gemini 1.5 Pro (May 2024) | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 52.8 | 32.1 |
| Released | 2026-09-09 | 2024-02-15 |
| Weights | Open | Proprietary |
| Context window | 1M | — |
| Max output | 393K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 37 | 45 |
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 1.5 Pro (May 2024): 34.2 (#241)
| Benchmark | DeepSeek V4.1 Flash | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Coding | 1506 | 1294 |
| LMArena WebDev | 1619 | — |
| SciCode | 51.9% | — |
| WeirdML | — | 22.2% |
| BigCodeBench Instruct | — | 43.8% |
| BigCodeBench Complete | — | 57.5% |
| CadEval | — | 34% |
| ALE-Bench | 1,092 | — |
| HumanEval+ | — | 79.3% |
| MBPP+ | — | 74.6% |
Agentic & Tool Use DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 31.2 (#69), Gemini 1.5 Pro (May 2024): 17.9 (#145)
| Benchmark | DeepSeek V4.1 Flash | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| APEX-Agents | 39.5% | — |
| TheAgentCompany | — | 3.4% |
| Cybench | — | 7.5% |
| BALROG | — | 21% |
| GDP.pdf | 19.8% | — |
Reasoning DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 50.2 (#36), Gemini 1.5 Pro (May 2024): 12.3 (#338)
| Benchmark | DeepSeek V4.1 Flash | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Hard Prompts | 1483 | 1296 |
| DTBench | 89.9% | 59% |
| Epoch Capabilities Index | 154.9 | 131.73 |
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 27.1% |
| NYT Connections (extended) | 89.6% | — |
| CritPt | 14.3% | — |
| Mystery Game Puzzles | 43% | — |
| LMCA | 47% | — |
| Surface Evolver Bench | 46.3% | — |
| BIG-Bench Hard | — | 89.2% |
| ForecastBench | — | 58.4 |
Math DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 66.7 (#25), Gemini 1.5 Pro (May 2024): 25.8 (#266)
| Benchmark | DeepSeek V4.1 Flash | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.3% | 23.1% |
| LMArena Math | 1477 | 1315 |
| FrontierMath (Tiers 1-3) | 67.4% | — |
| FrontierMath Tier 4 | 26.8% | — |
| ProofBench | 54% | — |
| Omni-MATH | — | 36.4% |
| MATH Level 5 | — | 70.4% |
Knowledge DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 57.9 (#38), Gemini 1.5 Pro (May 2024): 29.4 (#239)
| Benchmark | DeepSeek V4.1 Flash | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| GPQA Diamond | 89.8% | 57.2% |
| LMArena Expert | 1506 | 1279 |
| Humanity's Last Exam | — | 4.6% |
| MMLU-Pro | — | 73.7% |
| Confabulations | — | 13.5% |
| GPQA (HELM) | — | 53.4% |
| MMLU | — | 86.9% |
Multimodal DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 39.1 (#61), Gemini 1.5 Pro (May 2024): 36.8 (#77)
| Benchmark | DeepSeek V4.1 Flash | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Vision | 1277 | 1161 |
| Video-MME | — | 75% |
| Furniture Assembly | 34.2% | — |
Multilingual DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 55.0 (#35), Gemini 1.5 Pro (May 2024): 45.3 (#174)
| Benchmark | DeepSeek V4.1 Flash | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Non-English | 1448 | 1312 |
| LMArena Chinese | 1497 | 1331 |
| LMArena French | 1452 | 1302 |
| LMArena German | 1484 | 1286 |
| LMArena Japanese | 1412 | 1292 |
| LMArena Korean | 1452 | 1298 |
| LMArena Russian | 1471 | 1320 |
| LMArena Spanish | 1459 | 1311 |
Instruction Following DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 77.3 (#26), Gemini 1.5 Pro (May 2024): 68.6 (#185)
| Benchmark | DeepSeek V4.1 Flash | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Instruction Following | 1474 | 1297 |
| IFEval | — | 83.7% |
Long Context DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 45.2 (#47), Gemini 1.5 Pro (May 2024): 39.8 (#169)
| Benchmark | DeepSeek V4.1 Flash | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Longer Query | 1475 | 1308 |
Writing & Preference DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 65.4 (#48), Gemini 1.5 Pro (May 2024): 52.4 (#172)
| Benchmark | DeepSeek V4.1 Flash | Gemini 1.5 Pro (May 2024) |
|---|---|---|
| LMArena Text | 1462 | 1319 |
| LMArena Creative Writing | 1435 | 1333 |
| LMArena Multi-Turn | 1457 | 1296 |
| EQ-Bench Creative Writing | 1540 | — |
| WildBench | — | 81.3% |
Frequently asked questions
Is DeepSeek V4.1 Flash better than Gemini 1.5 Pro (May 2024)?
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 32.1 on the Noometry Index.
Is DeepSeek V4.1 Flash or Gemini 1.5 Pro (May 2024) better for coding?
DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 34.2 in the Noometry coding category.
How many benchmarks do DeepSeek V4.1 Flash and Gemini 1.5 Pro (May 2024) share?
22 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and Gemini 1.5 Pro (May 2024) has 45.