DeepSeek-V3.2-Exp
| Released | 2025-09-29 |
|---|---|
| Price per 1M | Not listed |
| Overall score | 47.9 · rank 130 |
| Provider | DeepSeek |
| Weights | Open weights |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 47.9 | 130 | 9 |
| Overall: Coding | 46.4 | 142 | 7 |
| Overall: Reasoning | 48.8 | 124 | 2 |
| Overall: Agentic work | 48.0 | 129 | 6 |
| Overall: Frontend | 39.5 | 176 | 3 |
| Coding | 48.7 | 125 | 2 |
| Agents | 47.5 | 125 | 2 |
| Reasoning | 48.8 | 124 | 2 |
| Frontend | 34.9 | 124 | 1 |
| General | 51.8 | 88 | 2 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 46.8 ±2.5 | 7 |
| Thinking | 50.0 ±3.7 | 4 |
Evidence
Coding 48.7 ±1.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Aider Polyglot | 74.2% | Epoch AI | 2026-11-11 |
| SciCode | 38.9% | Epoch AI | 2026-11-11 |
Agents 47.5 ±3.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| BFCL v4 | 56.7% | BFCL | 2026-04-12 |
| Vending-Bench 2 | $1,034 | Epoch AI | 2026-11-11 |
Reasoning 48.8 ±4.4
| Benchmark | Result | Source | Date |
|---|---|---|---|
| CritPt | 2.9% | Epoch AI | 2026-11-11 |
| Kagi Reasoning Benchmark | 52.2% | Kagi | 2026-11-11 |
Frontend 34.9 ±3.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena WebDev | 1,270 | LMArena | 2026-11-09 |
General 51.8 ±3.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Text | 1,425 | LMArena | 2026-11-09 |
| EQ-Bench Longform Creative Writing | 60.2% | EQ-Bench | 2026-11-11 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| Aider Polyglot | 70.2% | Epoch AI | A stronger configuration result was used |
| BFCL v4 | 54.1% | BFCL | A stronger configuration result was used |
| LMArena Text | 1,422 | LMArena | A stronger configuration result was used |
Names matched to this model
deepseek-v3-2-exp