Model comparison
DeepSeek-V2.5 (Sep 2024) vs DeepSeek V4.1 Flash
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 37.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeekSummary
- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 0 categories and DeepSeek V4.1 Flash in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4.1 Flash leads 66.7 to 35.9.
Side by side
| DeepSeek-V2.5 (Sep 2024) | DeepSeek V4.1 Flash | |
|---|---|---|
| Provider | DeepSeek | DeepSeek |
| Noometry Index | 37.6 | 52.8 |
| Released | 2024-09-06 | 2026-09-09 |
| Weights | Open | Open |
| Context window | — | 1M |
| Max output | — | 393K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.60 |
| Results tracked | 22 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4.1 Flash leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), DeepSeek V4.1 Flash: 52.9 (#32)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Coding | 1309 | 1506 |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1619 |
| SciCode | — | 51.9% |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| ALE-Bench | — | 1,092 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Agentic & Tool Use Not comparable
DeepSeek-V2.5 (Sep 2024): —, DeepSeek V4.1 Flash: 31.2 (#69)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | DeepSeek V4.1 Flash |
|---|---|---|
| APEX-Agents | — | 39.5% |
| GDP.pdf | — | 19.8% |
Reasoning DeepSeek V4.1 Flash leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), DeepSeek V4.1 Flash: 50.2 (#36)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1483 |
| NYT Connections (extended) | — | 89.6% |
| CritPt | — | 14.3% |
| Mystery Game Puzzles | — | 43% |
| DTBench | — | 89.9% |
| LMCA | — | 47% |
| Surface Evolver Bench | — | 46.3% |
| Epoch Capabilities Index | — | 154.9 |
Math DeepSeek V4.1 Flash leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), DeepSeek V4.1 Flash: 66.7 (#25)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Math | 1288 | 1477 |
| FrontierMath (Tiers 1-3) | — | 67.4% |
| FrontierMath Tier 4 | — | 26.8% |
| OTIS Mock AIME 2024-2025 | — | 98.3% |
| ProofBench | — | 54% |
Knowledge DeepSeek V4.1 Flash leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), DeepSeek V4.1 Flash: 57.9 (#38)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Expert | 1266 | 1506 |
| GPQA Diamond | — | 89.8% |
Multimodal Not comparable
DeepSeek-V2.5 (Sep 2024): —, DeepSeek V4.1 Flash: 39.1 (#61)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Vision | — | 1277 |
| Furniture Assembly | — | 34.2% |
Multilingual DeepSeek V4.1 Flash leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), DeepSeek V4.1 Flash: 55.0 (#35)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Non-English | 1273 | 1448 |
| LMArena Chinese | 1318 | 1497 |
| LMArena French | 1289 | 1452 |
| LMArena German | 1258 | 1484 |
| LMArena Japanese | 1228 | 1412 |
| LMArena Korean | 1209 | 1452 |
| LMArena Russian | 1289 | 1471 |
| LMArena Spanish | 1248 | 1459 |
Instruction Following DeepSeek V4.1 Flash leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), DeepSeek V4.1 Flash: 77.3 (#26)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Instruction Following | 1280 | 1474 |
Long Context DeepSeek V4.1 Flash leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), DeepSeek V4.1 Flash: 45.2 (#47)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Longer Query | 1301 | 1475 |
Writing & Preference DeepSeek V4.1 Flash leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), DeepSeek V4.1 Flash: 65.4 (#48)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | DeepSeek V4.1 Flash |
|---|---|---|
| LMArena Text | 1294 | 1462 |
| LMArena Creative Writing | 1285 | 1435 |
| LMArena Multi-Turn | 1297 | 1457 |
| EQ-Bench Creative Writing | — | 1540 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than DeepSeek V4.1 Flash?
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or DeepSeek V4.1 Flash better for coding?
DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and DeepSeek V4.1 Flash share?
17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and DeepSeek V4.1 Flash has 37.