Model comparison
DeepSeek V4 Flash vs Gemma 4 31B IT
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 43.5 on the Noometry Index. Gemma 4 31B IT costs 1.7× less per token, which makes it the better buy when DeepSeek V4 Flash's lead doesn't matter for your workload.
Last verified . 29 shared benchmarks.
DeepSeek
GoogleSummary
- They share 29 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 5 categories and Gemma 4 31B IT in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4 Flash leads 53.7 to 27.2.
- The biggest single-benchmark swing is Chess Puzzles: 33% for DeepSeek V4 Flash and 5% for Gemma 4 31B IT.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $0.15 / $0.60 for DeepSeek V4 Flash.
- DeepSeek V4 Flash accepts more context: 1M tokens versus 262K.
Side by side
| DeepSeek V4 Flash | Gemma 4 31B IT | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 53.6 | 43.5 |
| Released | 2026-04-24 | 2026-04-02 |
| Weights | Open | Open |
| Context window | 1M | 262K |
| Max output | 393K | 33K |
| Input $ / M tokens | $0.15 | $0.09 |
| Output $ / M tokens | $0.60 | $0.34 |
| Results tracked | 41 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Flash leads
DeepSeek V4 Flash: 47.9 (#59), Gemma 4 31B IT: 42.3 (#108)
| Benchmark | DeepSeek V4 Flash | Gemma 4 31B IT |
|---|---|---|
| LMArena WebDev | 1582 | 1366 |
| SciCode | 49.9% | 43.4% |
| WeirdML | 63% | 52.3% |
| LMArena Coding | 1457 | 1459 |
| ALE-Bench | 1,306 | 925.5 |
| FrontierCode | 18.8% | — |
Reasoning DeepSeek V4 Flash leads
DeepSeek V4 Flash: 53.7 (#30), Gemma 4 31B IT: 27.2 (#122)
| Benchmark | DeepSeek V4 Flash | Gemma 4 31B IT |
|---|---|---|
| Kagi LLM Benchmark | 52.2% | 63.5% |
| NYT Connections (extended) | 89.6% | 70.6% |
| CritPt | 16.6% | 1.4% |
| Chess Puzzles | 33% | 5% |
| LMArena Hard Prompts | 1444 | 1448 |
| DTBench | 90.9% | 82.7% |
| LMCA | 41.7% | 39.3% |
| Epoch Capabilities Index | 154.49 | 142.74 |
| ARC-AGI-2 | 61.4% | — |
| SimpleBench | 61.1% | — |
| ARC-AGI-1 | 89% | — |
| Thematic Generalization | — | 53% |
| Mystery Game Puzzles | 34% | — |
| Surface Evolver Bench | — | 30.6% |
Math DeepSeek V4 Flash leads
DeepSeek V4 Flash: 60.3 (#37), Gemma 4 31B IT: 43.2 (#81)
| Benchmark | DeepSeek V4 Flash | Gemma 4 31B IT |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 94.4% | 73.3% |
| LMArena Math | 1427 | 1465 |
| FrontierMath (Tiers 1-3) | 57.5% | — |
| FrontierMath Tier 4 | 24.4% | — |
| MathArena Final-Answer Competitions | 76.5% | — |
| ProofBench | 56% | — |
Knowledge DeepSeek V4 Flash leads
DeepSeek V4 Flash: 55.4 (#48), Gemma 4 31B IT: 37.9 (#151)
| Benchmark | DeepSeek V4 Flash | Gemma 4 31B IT |
|---|---|---|
| GPQA Diamond | 91% | 75.8% |
| SimpleQA Verified | 33.6% | 10.4% |
| LMArena Expert | 1441 | 1465 |
| Vectara Hallucination Rate | — | 7.4% |
Multimodal Not comparable
DeepSeek V4 Flash: —, Gemma 4 31B IT: 41.6 (#34)
| Benchmark | DeepSeek V4 Flash | Gemma 4 31B IT |
|---|---|---|
| LMArena Vision | — | 1277 |
| LMArena Document | — | 1425 |
Multilingual Too close to call
DeepSeek V4 Flash: 53.0 (#72), Gemma 4 31B IT: 53.8 (#57)
| Benchmark | DeepSeek V4 Flash | Gemma 4 31B IT |
|---|---|---|
| LMArena Non-English | 1420 | 1431 |
| LMArena Chinese | 1468 | 1476 |
| LMArena French | 1439 | 1435 |
| LMArena Russian | 1428 | 1460 |
| LMArena Spanish | 1436 | 1444 |
| LMArena German | 1418 | — |
| LMArena Japanese | 1406 | — |
| LMArena Korean | 1384 | — |
Instruction Following Too close to call
DeepSeek V4 Flash: 74.9 (#81), Gemma 4 31B IT: 75.5 (#61)
| Benchmark | DeepSeek V4 Flash | Gemma 4 31B IT |
|---|---|---|
| LMArena Instruction Following | 1421 | 1433 |
Long Context Too close to call
DeepSeek V4 Flash: 43.8 (#85), Gemma 4 31B IT: 44.2 (#71)
| Benchmark | DeepSeek V4 Flash | Gemma 4 31B IT |
|---|---|---|
| LMArena Longer Query | 1434 | 1446 |
Writing & Preference DeepSeek V4 Flash leads
DeepSeek V4 Flash: 63.8 (#61), Gemma 4 31B IT: 60.5 (#96)
| Benchmark | DeepSeek V4 Flash | Gemma 4 31B IT |
|---|---|---|
| LMArena Text | 1432 | 1443 |
| LMArena Creative Writing | 1403 | 1415 |
| EQ-Bench Creative Writing | 1559 | 1368 |
| LMArena Multi-Turn | 1449 | 1452 |
| EQ-Bench 4 | — | 1120 |
Frequently asked questions
Is DeepSeek V4 Flash better than Gemma 4 31B IT?
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 43.5 on the Noometry Index. Gemma 4 31B IT costs 1.7× less per token, which makes it the better buy when DeepSeek V4 Flash's lead doesn't matter for your workload.
Which is cheaper, DeepSeek V4 Flash or Gemma 4 31B IT?
Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; DeepSeek V4 Flash lists at $0.15 and $0.60.
Is DeepSeek V4 Flash or Gemma 4 31B IT better for coding?
DeepSeek V4 Flash scores higher on coding benchmarks: 47.9 versus 42.3 in the Noometry coding category.
Which has the bigger context window?
DeepSeek V4 Flash does, with 1M tokens against 262K.
How many benchmarks do DeepSeek V4 Flash and Gemma 4 31B IT share?
29 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and Gemma 4 31B IT has 35.