Model comparison
DeepSeek-V3.2-Exp vs Llama 3.2 1B
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.9 to 19.9 on the Noometry Index. Llama 3.2 1B costs 4.1× less per token, which makes it the better buy when DeepSeek-V3.2-Exp's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
DeepSeek
MetaSummary
- They share 19 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 9 categories and Llama 3.2 1B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-V3.2-Exp leads 51.6 to 7.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 87.8% for DeepSeek-V3.2-Exp and 0.6% for Llama 3.2 1B.
- Llama 3.2 1B is cheaper at $0.027 / $0.20 per million input/output tokens, against $0.26 / $0.38 for DeepSeek-V3.2-Exp.
- DeepSeek-V3.2-Exp accepts more context: 164K tokens versus 60K.
Side by side
| DeepSeek-V3.2-Exp | Llama 3.2 1B | |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 44.9 | 19.9 |
| Released | 2025-09-29 | 2024-09-24 |
| Weights | Open | Open |
| Context window | 164K | 60K |
| Max output | 66K | 54K |
| Input $ / M tokens | $0.26 | $0.027 |
| Output $ / M tokens | $0.38 | $0.20 |
| Results tracked | 48 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 46.4 (#61), Llama 3.2 1B: 20.6 (#333)
| Benchmark | DeepSeek-V3.2-Exp | Llama 3.2 1B |
|---|---|---|
| LMArena Coding | 1454 | 1071 |
| SWE-bench Verified (bash only) | 70% | — |
| Aider Polyglot | 74.2% | — |
| LMArena WebDev | 1362 | — |
| SWE-bench Multilingual | 59% | — |
| SciCode | 38.9% | — |
| WeirdML | 39.5% | — |
| BigCodeBench Instruct | — | 8.2% |
| BigCodeBench Complete | — | 11.3% |
Agentic & Tool Use DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 37.9 (#31), Llama 3.2 1B: 14.5 (#142)
| Benchmark | DeepSeek-V3.2-Exp | Llama 3.2 1B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 56.7% | 10.8% |
| Terminal-Bench | 39.6% | — |
| TheAgentCompany | 42.9% | — |
| BALROG | — | 6.6% |
| Vending-Bench 2 | 1,034 | — |
Reasoning DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 22.0 (#185), Llama 3.2 1B: 15.6 (#304)
| Benchmark | DeepSeek-V3.2-Exp | Llama 3.2 1B |
|---|---|---|
| Chess Puzzles | 14% | 0% |
| LMArena Hard Prompts | 1433 | 1044 |
| Epoch Capabilities Index | 146.28 | 101.95 |
| ARC-AGI-2 | 4% | — |
| Kagi LLM Benchmark | 52.2% | — |
| NYT Connections (extended) | 36.7% | — |
| ARC-AGI-1 | 57% | — |
| CritPt | 2.9% | — |
| Thematic Generalization | 65% | — |
| DTBench | 87.7% | — |
| LMCA | 29.1% | — |
Math DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 40.8 (#75), Llama 3.2 1B: 9.7 (#308)
| Benchmark | DeepSeek-V3.2-Exp | Llama 3.2 1B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 87.8% | 0.6% |
| LMArena Math | 1435 | 1086 |
| MathArena Final-Answer Competitions | 57.7% | — |
| ProofBench | 8% | — |
| 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), Llama 3.2 1B: 7.2 (#307)
| Benchmark | DeepSeek-V3.2-Exp | Llama 3.2 1B |
|---|---|---|
| GPQA Diamond | 83.4% | 23.9% |
| LMArena Expert | 1436 | 1007 |
| Vectara Hallucination Rate | 5.3% | — |
Multilingual DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 52.4 (#85), Llama 3.2 1B: 23.9 (#287)
| Benchmark | DeepSeek-V3.2-Exp | Llama 3.2 1B |
|---|---|---|
| LMArena Non-English | 1409 | 973 |
| LMArena Chinese | 1461 | 958 |
| LMArena German | 1440 | 1014 |
| LMArena Russian | 1423 | 941 |
| LMArena French | 1435 | — |
| LMArena Japanese | 1377 | — |
| LMArena Korean | 1372 | — |
| LMArena Spanish | 1441 | — |
Instruction Following DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 74.7 (#89), Llama 3.2 1B: 52.6 (#285)
| Benchmark | DeepSeek-V3.2-Exp | Llama 3.2 1B |
|---|---|---|
| LMArena Instruction Following | 1413 | 1031 |
Long Context DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 47.6 (#15), Llama 3.2 1B: 31.9 (#269)
| Benchmark | DeepSeek-V3.2-Exp | Llama 3.2 1B |
|---|---|---|
| LMArena Longer Query | 1428 | 1050 |
| Fiction.LiveBench | 83.3% | — |
| CL-bench | 13.2% | — |
| CL-bench Life | 9.5% | — |
Writing & Preference DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 62.5 (#73), Llama 3.2 1B: 21.4 (#305)
| Benchmark | DeepSeek-V3.2-Exp | Llama 3.2 1B |
|---|---|---|
| LMArena Text | 1425 | 1055 |
| LMArena Creative Writing | 1403 | 1033 |
| EQ-Bench Creative Writing | 1515 | 200 |
| LMArena Multi-Turn | 1427 | 1030 |
Frequently asked questions
Is DeepSeek-V3.2-Exp better than Llama 3.2 1B?
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.9 to 19.9 on the Noometry Index. Llama 3.2 1B costs 4.1× less per token, which makes it the better buy when DeepSeek-V3.2-Exp's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-V3.2-Exp or Llama 3.2 1B?
Llama 3.2 1B is cheaper. It lists at $0.027 per million input tokens and $0.20 per million output tokens; DeepSeek-V3.2-Exp lists at $0.26 and $0.38.
Is DeepSeek-V3.2-Exp or Llama 3.2 1B better for coding?
DeepSeek-V3.2-Exp scores higher on coding benchmarks: 46.4 versus 20.6 in the Noometry coding category.
Which has the bigger context window?
DeepSeek-V3.2-Exp does, with 164K tokens against 60K.
How many benchmarks do DeepSeek-V3.2-Exp and Llama 3.2 1B share?
19 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 48 scored results on Noometry and Llama 3.2 1B has 22.