Model comparison
DeepSeek Coder 1.3B vs DeepSeek V4 Pro
DeepSeek V4 Pro has enough public results to be ranked (#31); DeepSeek Coder 1.3B does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
DeepSeekSummary
- They share 1 benchmark with published results for both. DeepSeek Coder 1.3B scores higher in 0 categories and DeepSeek V4 Pro in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek V4 Pro leads 52.4 to 31.2.
Side by side
| DeepSeek Coder 1.3B | DeepSeek V4 Pro | |
|---|---|---|
| Provider | DeepSeek | DeepSeek |
| Noometry Index | 35.0 | 54.3 |
| Released | 2023-11-02 | 2026-04-24 |
| Weights | Open | Open |
| Context window | — | 1M |
| Max output | — | 393K |
| Input $ / M tokens | — | $0.66 |
| Output $ / M tokens | — | $1.98 |
| Results tracked | 9 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Pro leads
DeepSeek Coder 1.3B: 31.2 (#287), DeepSeek V4 Pro: 52.4 (#34)
| Benchmark | DeepSeek Coder 1.3B | DeepSeek V4 Pro |
|---|---|---|
| SWE-bench Verified | — | 77.6% |
| FrontierCode | — | 28.6% |
| LMArena WebDev | — | 1582 |
| SciCode | — | 51% |
| WeirdML | — | 66.2% |
| BigCodeBench Instruct | 22.8% | — |
| LMArena Coding | — | 1470 |
| BigCodeBench Complete | 29.6% | — |
| ALE-Bench | — | 1,403 |
| HumanEval+ | 60.4% | — |
| MBPP+ | 54.8% | — |
Agentic & Tool Use Not comparable
DeepSeek Coder 1.3B: —, DeepSeek V4 Pro: 32.8 (#58)
| Benchmark | DeepSeek Coder 1.3B | DeepSeek V4 Pro |
|---|---|---|
| APEX-Agents | — | 47.3% |
| Vending-Bench 2 | — | 3,285 |
Reasoning Not comparable
DeepSeek Coder 1.3B: —, DeepSeek V4 Pro: 56.5 (#24)
| Benchmark | DeepSeek Coder 1.3B | DeepSeek V4 Pro |
|---|---|---|
| Epoch Capabilities Index | 63.6 | 155.31 |
| ARC-AGI-2 | — | 61.3% |
| Kagi LLM Benchmark | — | 53.5% |
| NYT Connections (extended) | — | 91.3% |
| ARC-AGI-1 | — | 90.5% |
| CritPt | — | 18% |
| Chess Puzzles | — | 47% |
| LMArena Hard Prompts | — | 1461 |
| Mystery Game Puzzles | — | 43% |
| DTBench | — | 93.9% |
| LMCA | — | 45.5% |
| Surface Evolver Bench | — | 40% |
| ForecastBench | — | 56.1 |
| WinoGrande | 53.3% | — |
Math Not comparable
DeepSeek Coder 1.3B: —, DeepSeek V4 Pro: 64.8 (#30)
| Benchmark | DeepSeek Coder 1.3B | DeepSeek V4 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 64.6% |
| FrontierMath Tier 4 | — | 26.8% |
| MathArena Final-Answer Competitions | — | 76.6% |
| OTIS Mock AIME 2024-2025 | — | 98.6% |
| ProofBench | — | 50% |
| LMArena Math | — | 1455 |
| GSM8K | 4.4% | — |
Knowledge Not comparable
DeepSeek Coder 1.3B: —, DeepSeek V4 Pro: 59.5 (#31)
| Benchmark | DeepSeek Coder 1.3B | DeepSeek V4 Pro |
|---|---|---|
| GPQA Diamond | — | 91.7% |
| SimpleQA Verified | — | 52.9% |
| Vectara Hallucination Rate | — | 8.6% |
| LMArena Expert | — | 1464 |
| ARC (AI2) Challenge | 25.4% | — |
| MMLU | 25.8% | — |
Multilingual Not comparable
DeepSeek Coder 1.3B: —, DeepSeek V4 Pro: 54.4 (#45)
| Benchmark | DeepSeek Coder 1.3B | DeepSeek V4 Pro |
|---|---|---|
| LMArena Non-English | — | 1439 |
| LMArena Chinese | — | 1486 |
| LMArena French | — | 1472 |
| LMArena German | — | 1458 |
| LMArena Japanese | — | 1445 |
| LMArena Korean | — | 1447 |
| LMArena Russian | — | 1453 |
| LMArena Spanish | — | 1458 |
Instruction Following Not comparable
DeepSeek Coder 1.3B: —, DeepSeek V4 Pro: 76.1 (#47)
| Benchmark | DeepSeek Coder 1.3B | DeepSeek V4 Pro |
|---|---|---|
| LMArena Instruction Following | — | 1448 |
Long Context Not comparable
DeepSeek Coder 1.3B: —, DeepSeek V4 Pro: 45.0 (#51)
| Benchmark | DeepSeek Coder 1.3B | DeepSeek V4 Pro |
|---|---|---|
| CL-bench Life | — | 13.5% |
| LMArena Longer Query | — | 1458 |
Writing & Preference Not comparable
DeepSeek Coder 1.3B: —, DeepSeek V4 Pro: 65.5 (#46)
| Benchmark | DeepSeek Coder 1.3B | DeepSeek V4 Pro |
|---|---|---|
| LMArena Text | — | 1451 |
| LMArena Creative Writing | — | 1446 |
| EQ-Bench Creative Writing | — | 1553 |
| EQ-Bench 4 | — | 1166 |
| LMArena Multi-Turn | — | 1467 |
Frequently asked questions
Is DeepSeek Coder 1.3B better than DeepSeek V4 Pro?
DeepSeek V4 Pro has enough public results to be ranked (#31); DeepSeek Coder 1.3B does not yet, so treat this comparison as directional.
Is DeepSeek Coder 1.3B or DeepSeek V4 Pro better for coding?
DeepSeek V4 Pro scores higher on coding benchmarks: 52.4 versus 31.2 in the Noometry coding category.
How many benchmarks do DeepSeek Coder 1.3B and DeepSeek V4 Pro share?
1 benchmark has published results for both models. DeepSeek Coder 1.3B has 9 scored results on Noometry and DeepSeek V4 Pro has 48.