DeepSeek V4 Pro 0423 vs Gemma 4 31B
Updated October 21, 2026. 41 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick Gemma 4 31B for coding: it scores 38.3 on the Vibe Coding Index against 35.3 for DeepSeek V4 Pro 0423.
Pick DeepSeek V4 Pro 0423 when the context window is larger, 1.05M against 262K tokens, or when what matters is LMArena WebDev or AA Coding Index, where it leads.
- Shared results
- 41
- DeepSeek V4 Pro 0423 only
- 42
- Gemma 4 31B only
- 27
- Like-for-like categories
- 7 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, four public coding benchmarks
Gemma 4 31B
Gemma 4 31B scores 38.3 against 35.3.
1 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
DeepSeek V4 Pro 0423
DeepSeek V4 Pro 0423 leads, 30.4 against 14.7.
Same board, both measured
Agentic work
AA Agentic Index
DeepSeek V4 Pro 0423
DeepSeek V4 Pro 0423 leads, 26.3 against 4.2.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only DeepSeek V4 Pro 0423 has a GPQA Diamond result, 89.4%.
Directional only
Knowledge
MMLU Pro
No call
Only DeepSeek V4 Pro 0423 has a MMLU Pro result, 87.3%.
Directional only
Web design
Design Arena: websites
No call
Only DeepSeek V4 Pro 0423 has a Design Arena: websites result, 1235.
Directional only
Long documents
Listed context window
DeepSeek V4 Pro 0423
DeepSeek V4 Pro 0423 takes 1.05M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemma 4 31B
DeepSeek V4 Pro 0423 $0.0019, Gemma 4 31B $0.0004 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only DeepSeek V4 Pro 0423 has the number, $0.57.
Directional only
At a glance
- Coding index
- DeepSeek V4 Pro 0423 35.3 from 1 benchmark, Gemma 4 31B 38.3 from 2 benchmarks.
- Widest category
- Agentic work, 22.1 points apart on average over 1 shared benchmark.
- Widest single gap
- SimpleQA Verified: DeepSeek V4 Pro 0423 47.0% against Gemma 4 31B 10.4%, 36.6 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V4 Pro 0423 $1.9105 against Gemma 4 31B $0.40 per million output tokens, 4.8x apart.
- Context window
- DeepSeek V4 Pro 0423 takes 1.05M tokens, Gemma 4 31B 262K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | DeepSeek V4 Pro 0423 | Bars | Gemma 4 31B | Ties |
|---|---|---|---|---|
| Coding | 7 | 1 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 3 | 1 | ||
| Math | 1 | 2 | ||
| Knowledge | 6 | 0 | ||
| General | 16 | 1 | ||
| All shared boards | 36 | 5 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index71
| Benchmark | DeepSeek V4 Pro 0423 | Gemma 4 31B | Leader |
|---|---|---|---|
| LiveBench coding | Not measured | 49.0% | Only Gemma 4 31B measured |
| LMArena WebDev | 1447 | 1367 | DeepSeek V4 Pro 0423 |
| AA Coding Index | 59.4 | 43.4 | DeepSeek V4 Pro 0423 |
| LiveCodeBench (Vals AI) | 87.5% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| SWE-bench Verified (Vals AI) | 77.4% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Terminal-Bench 4 (Vals AI) | 11.1% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Vibe Code Bench (Vals AI) | 49.9% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Code migration (Vals AI) | 26.2% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Terminal-Bench 2.1 (Vals AI) | 50.2% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| SkillsBench (Vals AI) | 51.3% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| SciCode | Not measured | 45.5% | Only Gemma 4 31B measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 36.4% | Only Gemma 4 31B measured |
| FrontierCode | 17.6% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| WeirdML | 48.9% | 52.3% | Gemma 4 31B |
| ALE-Bench | 1006.1 | 925.5 | DeepSeek V4 Pro 0423 |
| LMArena Text: coding | 1470 | 1459 | DeepSeek V4 Pro 0423 |
| LMArena Text: software and IT | 1469 | 1463 | DeepSeek V4 Pro 0423 |
| LMArena WebDev: React | 1441 | 1359 | DeepSeek V4 Pro 0423 |
| LMArena WebDev: HTML | 1435 | 1380 | DeepSeek V4 Pro 0423 |
| Neither model has a result on the other 18 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | DeepSeek V4 Pro 0423 | Gemma 4 31B | Leader |
|---|---|---|---|
| AA Intelligence Index | 30.4 | 14.7 | DeepSeek V4 Pro 0423 |
| Epoch Capabilities Index | 149.1 | 143.0 | DeepSeek V4 Pro 0423 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | DeepSeek V4 Pro 0423 | Gemma 4 31B | Leader |
|---|---|---|---|
| AA Agentic Index | 26.3 | 4.2 | DeepSeek V4 Pro 0423 |
| Design Arena: agents building web apps | 1000 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: agents building full-stack apps | 948 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: agents building Godot games | 1059 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LiveBench research | Not measured | 44.4% | Only Gemma 4 31B measured |
| LiveBench browser | Not measured | 4.0% | Only Gemma 4 31B measured |
| LiveBench long agentic | Not measured | 13.3% | Only Gemma 4 31B measured |
| Finance Agent (Vals AI) | 44.1% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Tax Agent Bench (Vals AI) | 25.2% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Legal Research Bench (Vals AI) | 23.1% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Excel Modeling Benchmark (Vals AI) | 51.6% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| τ²-Bench Telecom | Not measured | 65.5% | Only Gemma 4 31B measured |
| Vending-Bench 2 | $3,285 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Neither model has a result on the other 26 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index31
| Benchmark | DeepSeek V4 Pro 0423 | Gemma 4 31B | Leader |
|---|---|---|---|
| GPQA Diamond | 89.4% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LiveBench reasoning | Not measured | 68.3% | Only Gemma 4 31B measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 85.7% | Only Gemma 4 31B measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 23.6% | Only Gemma 4 31B measured |
| GPQA Diamond (Epoch AI run) | 90.9% | 75.8% | DeepSeek V4 Pro 0423 |
| Chess puzzles | 19.0% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Mystery game puzzles | 17.0% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LMArena Text: hard prompts | 1461 | 1448 | DeepSeek V4 Pro 0423 |
| LMArena Text: expert | 1463 | 1464 | Gemma 4 31B |
| LMArena Text: hard prompts in English | 1466 | 1456 | DeepSeek V4 Pro 0423 |
| LMArena Vision: diagrams | Not measured | 1283 | Only Gemma 4 31B measured |
| LMArena Vision: homework | Not measured | 1310 | Only Gemma 4 31B measured |
| Neither model has a result on the other 9 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index12
| Benchmark | DeepSeek V4 Pro 0423 | Gemma 4 31B | Leader |
|---|---|---|---|
| OTIS Mock AIME | 96.7% | 73.3% | DeepSeek V4 Pro 0423 |
| FrontierMath, tiers 1 to 3 | 45.3% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| FrontierMath, tier 4 | 2.4% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| ProofBench | 16.0% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LMArena Text: math | 1443 | 1463 | Gemma 4 31B |
| LMArena Text: mathematical work | 1455 | 1465 | Gemma 4 31B |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | DeepSeek V4 Pro 0423 | Gemma 4 31B | Leader |
|---|---|---|---|
| MMLU Pro | 87.3% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LegalBench (Vals AI) | 80.3% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| CaseLaw (Vals AI) | 59.4% | 52.6% | DeepSeek V4 Pro 0423 |
| CorpFin (Vals AI) | 61.4% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| TaxEval (Vals AI) | 72.1% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| MortgageTax (Vals AI) | Not measured | 61.4% | Only Gemma 4 31B measured |
| MedCode (Vals AI) | 40.5% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| SimpleQA Verified | 47.0% | 10.4% | DeepSeek V4 Pro 0423 |
| LMArena Text: science | 1470 | 1457 | DeepSeek V4 Pro 0423 |
| LMArena Text: medicine and healthcare | 1466 | 1451 | DeepSeek V4 Pro 0423 |
| LMArena Text: legal and government | 1464 | 1438 | DeepSeek V4 Pro 0423 |
| LMArena Text: business and finance | 1443 | 1430 | DeepSeek V4 Pro 0423 |
| Neither model has a result on the other 5 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | DeepSeek V4 Pro 0423 | Gemma 4 31B | Leader |
|---|---|---|---|
| Design Arena: websites | 1235 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: UI components | 1221 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: game dev | 1229 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: data viz | 1203 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: 3D | 1254 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: all code categories | 1240 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: SVG | 1139 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| Design Arena: ASCII art | 1148 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LiveBench design | Not measured | 58.4% | Only Gemma 4 31B measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index161
| Benchmark | DeepSeek V4 Pro 0423 | Gemma 4 31B | Leader |
|---|---|---|---|
| LiveBench data analysis | Not measured | 53.3% | Only Gemma 4 31B measured |
| Public Benefits Bench (Vals AI) | 62.9% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| SAGE (Vals AI) | Not measured | 55.0% | Only Gemma 4 31B measured |
| MedScribe (Vals AI) | 75.1% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| IFBench | Not measured | 75.6% | Only Gemma 4 31B measured |
| Long context reasoning (AA-LCR) | Not measured | 69.7% | Only Gemma 4 31B measured |
| DTBench | 90.7% | 82.7% | DeepSeek V4 Pro 0423 |
| LMCA | 41.2% | 39.3% | DeepSeek V4 Pro 0423 |
| Surface Evolver Bench | 40.0% | 30.6% | DeepSeek V4 Pro 0423 |
| CL-bench Life | 13.5% | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LMArena Text | 1451 | 1443 | DeepSeek V4 Pro 0423 |
| LMArena Text: instruction following | 1445 | 1433 | DeepSeek V4 Pro 0423 |
| LMArena Text: creative writing | 1446 | 1417 | DeepSeek V4 Pro 0423 |
| LMArena Vision | Not measured | 1276 | Only Gemma 4 31B measured |
| LMArena Text: English | 1459 | 1451 | DeepSeek V4 Pro 0423 |
| LMArena Text: non-English | 1439 | 1430 | DeepSeek V4 Pro 0423 |
| LMArena Text: Chinese | 1481 | 1475 | DeepSeek V4 Pro 0423 |
| LMArena Text: German | 1458 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LMArena Text: Japanese | 1446 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LMArena Text: Korean | 1409 | Not measured | Only DeepSeek V4 Pro 0423 measured |
| LMArena Text: French | 1473 | 1436 | DeepSeek V4 Pro 0423 |
| LMArena Text: Spanish | 1457 | 1442 | DeepSeek V4 Pro 0423 |
| LMArena Text: Russian | 1453 | 1460 | Gemma 4 31B |
| LMArena Text: Polish | 1461 | 1433 | DeepSeek V4 Pro 0423 |
| LMArena Text: multi-turn | 1468 | 1452 | DeepSeek V4 Pro 0423 |
| LMArena Text: longer queries | 1458 | 1446 | DeepSeek V4 Pro 0423 |
| LMArena Text: writing and language | 1447 | 1432 | DeepSeek V4 Pro 0423 |
| LMArena Text: entertainment and media | 1431 | 1405 | DeepSeek V4 Pro 0423 |
| LMArena Vision: English | Not measured | 1271 | Only Gemma 4 31B measured |
| LMArena Vision: Chinese | Not measured | 1326 | Only Gemma 4 31B measured |
| LMArena Vision: reading text | Not measured | 1282 | Only Gemma 4 31B measured |
| LMArena Vision: humor | Not measured | 1280 | Only Gemma 4 31B measured |
| LMArena Vision: captioning | Not measured | 1218 | Only Gemma 4 31B measured |
| LMArena Vision: recognizing things | Not measured | 1226 | Only Gemma 4 31B measured |
| LMArena Vision: creative writing | Not measured | 1285 | Only Gemma 4 31B measured |
| LMArena Document | Not measured | 1425 | Only Gemma 4 31B measured |
| Neither model has a result on the other 10 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V4 Pro 0423 | Gemma 4 31B | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Gemma 4 31B costs less
Repository review
50K input + 3K output tokens
Gemma 4 31B costs less
Agent loop
200K input + 10K output tokens
Gemma 4 31B costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | DeepSeek V4 Pro 0423 | Google Gemma 4 31B |
|---|---|---|
| Maker | DeepSeek | |
| Weights | Open weights | Open weights |
| Released | April 24, 2026 | April 2, 2026 |
| Context window | 1.05M | 262K |
| Input $/Mtok | $0.9553 | $0.20 |
| Output $/Mtok | $1.9105 | $0.40 |
| Coding index | 35.3 | 38.3 |
| Independent measurements behind it | 1 | 2 |
| Cost per solved task | $0.57 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V4 Pro 0423 better than Gemma 4 31B for coding?
Pick Gemma 4 31B for coding: it scores 38.3 on the Vibe Coding Index against 35.3 for DeepSeek V4 Pro 0423. Pick DeepSeek V4 Pro 0423 when the context window is larger, 1.05M against 262K tokens, or when what matters is LMArena WebDev or AA Coding Index, where it leads.
Which is cheaper, DeepSeek V4 Pro 0423 or Gemma 4 31B?
DeepSeek V4 Pro 0423 costs $0.9553 per million input tokens and $1.9105 per million output tokens; Gemma 4 31B costs $0.20 and $0.40. Cost per solved task is known for DeepSeek V4 Pro 0423 only.
Which has the bigger context window, DeepSeek V4 Pro 0423 or Gemma 4 31B?
DeepSeek V4 Pro 0423, with 1.05M tokens against 262K.
How many benchmarks is the DeepSeek V4 Pro 0423 vs Gemma 4 31B comparison based on?
41 benchmarks have a result for both models as of October 21, 2026. DeepSeek V4 Pro 0423's coding index rests on 1 independent benchmark and Gemma 4 31B's on 2. Where only one model has a result, the page says so instead of naming a winner.