Model comparison
DeepSeek-V3.2-Exp vs Nova Premier 1.0
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.9 to 37.7 on the Noometry Index.
Last verified . 1 shared benchmarks.
DeepSeekSummary
- They share 1 benchmark with published results for both. DeepSeek-V3.2-Exp scores higher in 4 categories and Nova Premier 1.0 in 1 category; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-V3.2-Exp leads 51.6 to 35.4.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 52.2% for DeepSeek-V3.2-Exp and 44.8% for Nova Premier 1.0.
- DeepSeek-V3.2-Exp is cheaper at $0.26 / $0.38 per million input/output tokens, against $2.50 / $12.50 for Nova Premier 1.0.
- Nova Premier 1.0 accepts more context: 1M tokens versus 164K.
- DeepSeek-V3.2-Exp has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.2-Exp | Nova Premier 1.0 | |
|---|---|---|
| Provider | DeepSeek | Amazon |
| Noometry Index | 44.9 | 37.7 |
| Released | 2025-09-29 | 2025-04-30 |
| Weights | Open | Proprietary |
| Context window | 164K | 1M |
| Max output | 66K | 10K |
| Input $ / M tokens | $0.26 | $2.50 |
| Output $ / M tokens | $0.38 | $12.50 |
| Results tracked | 48 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
DeepSeek-V3.2-Exp: 46.4 (#61), Nova Premier 1.0: —
| Benchmark | DeepSeek-V3.2-Exp | Nova Premier 1.0 |
|---|---|---|
| SWE-bench Verified (bash only) | 70% | — |
| Aider Polyglot | 74.2% | — |
| LMArena WebDev | 1362 | — |
| SWE-bench Multilingual | 59% | — |
| SciCode | 38.9% | — |
| WeirdML | 39.5% | — |
| LMArena Coding | 1454 | — |
Agentic & Tool Use Not comparable
DeepSeek-V3.2-Exp: 37.9 (#31), Nova Premier 1.0: —
| Benchmark | DeepSeek-V3.2-Exp | Nova Premier 1.0 |
|---|---|---|
| Terminal-Bench | 39.6% | — |
| Berkeley Function Calling Leaderboard | 56.7% | — |
| TheAgentCompany | 42.9% | — |
| Vending-Bench 2 | 1,034 | — |
Reasoning Too close to call
DeepSeek-V3.2-Exp: 22.0 (#185), Nova Premier 1.0: 22.3 (#182)
| Benchmark | DeepSeek-V3.2-Exp | Nova Premier 1.0 |
|---|---|---|
| Kagi LLM Benchmark | 52.2% | 44.8% |
| ARC-AGI-2 | 4% | — |
| NYT Connections (extended) | 36.7% | — |
| ARC-AGI-1 | 57% | — |
| CritPt | 2.9% | — |
| Chess Puzzles | 14% | — |
| Thematic Generalization | 65% | — |
| LMArena Hard Prompts | 1433 | — |
| DTBench | 87.7% | — |
| LMCA | 29.1% | — |
| Epoch Capabilities Index | 146.28 | — |
Math DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 40.8 (#75), Nova Premier 1.0: 31.5 (#194)
| Benchmark | DeepSeek-V3.2-Exp | Nova Premier 1.0 |
|---|---|---|
| MathArena Final-Answer Competitions | 57.7% | — |
| OTIS Mock AIME 2024-2025 | 87.8% | — |
| ProofBench | 8% | — |
| Omni-MATH | — | 35% |
| LMArena Math | 1435 | — |
| FrontierMath (Feb 2025 set) | 22.1% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 51.6 (#61), Nova Premier 1.0: 35.4 (#176)
| Benchmark | DeepSeek-V3.2-Exp | Nova Premier 1.0 |
|---|---|---|
| GPQA Diamond | 83.4% | — |
| MMLU-Pro | — | 72.6% |
| Vectara Hallucination Rate | 5.3% | — |
| GPQA (HELM) | — | 51.8% |
| LMArena Expert | 1436 | — |
Multilingual Not comparable
DeepSeek-V3.2-Exp: 52.4 (#85), Nova Premier 1.0: —
| Benchmark | DeepSeek-V3.2-Exp | Nova Premier 1.0 |
|---|---|---|
| LMArena Non-English | 1409 | — |
| LMArena Chinese | 1461 | — |
| LMArena French | 1435 | — |
| LMArena German | 1440 | — |
| LMArena Japanese | 1377 | — |
| LMArena Korean | 1372 | — |
| LMArena Russian | 1423 | — |
| LMArena Spanish | 1441 | — |
Instruction Following DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 74.7 (#89), Nova Premier 1.0: 66.9 (#201)
| Benchmark | DeepSeek-V3.2-Exp | Nova Premier 1.0 |
|---|---|---|
| IFEval | — | 80.3% |
| LMArena Instruction Following | 1413 | — |
Long Context Not comparable
DeepSeek-V3.2-Exp: 47.6 (#15), Nova Premier 1.0: —
| Benchmark | DeepSeek-V3.2-Exp | Nova Premier 1.0 |
|---|---|---|
| Fiction.LiveBench | 83.3% | — |
| CL-bench | 13.2% | — |
| CL-bench Life | 9.5% | — |
| LMArena Longer Query | 1428 | — |
Writing & Preference DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 62.5 (#73), Nova Premier 1.0: 51.0 (#174)
| Benchmark | DeepSeek-V3.2-Exp | Nova Premier 1.0 |
|---|---|---|
| LMArena Text | 1425 | — |
| LMArena Creative Writing | 1403 | — |
| EQ-Bench Creative Writing | 1515 | — |
| WildBench | — | 78.8% |
| LMArena Multi-Turn | 1427 | — |
Frequently asked questions
Is DeepSeek-V3.2-Exp better than Nova Premier 1.0?
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.9 to 37.7 on the Noometry Index.
Which is cheaper, DeepSeek-V3.2-Exp or Nova Premier 1.0?
DeepSeek-V3.2-Exp is cheaper. It lists at $0.26 per million input tokens and $0.38 per million output tokens; Nova Premier 1.0 lists at $2.50 and $12.50.
Which has the bigger context window?
Nova Premier 1.0 does, with 1M tokens against 164K.
How many benchmarks do DeepSeek-V3.2-Exp and Nova Premier 1.0 share?
1 benchmark has published results for both models. DeepSeek-V3.2-Exp has 48 scored results on Noometry and Nova Premier 1.0 has 6.