Model comparison
DeepSeek-V3.1-Terminus vs Llama 2-13B
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 29.6 on the Noometry Index.
Last verified . 11 shared benchmarks.
DeepSeek
MetaSummary
- They share 11 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 7 categories and Llama 2-13B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.0 to 29.8.
- The biggest single-benchmark swing is DTBench: 81.3% for DeepSeek-V3.1-Terminus and 42.2% for Llama 2-13B.
Side by side
| DeepSeek-V3.1-Terminus | Llama 2-13B | |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 43.1 | 29.6 |
| Released | 2025-09-22 | 2023-07-18 |
| Weights | Open | Open |
| Context window | 164K | — |
| Max output | 147K | — |
| Input $ / M tokens | $0.27 | — |
| Output $ / M tokens | $1 | — |
| Results tracked | 16 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 42.0 (#113), Llama 2-13B: 30.9 (#291)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 2-13B |
|---|---|---|
| LMArena Coding | 1426 | 1062 |
| SciCode | 40.6% | — |
| ALE-Bench | 745.17 | — |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 26.4 (#133), Llama 2-13B: 12.8 (#337)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 2-13B |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1051 |
| DTBench | 81.3% | 42.2% |
| Kagi LLM Benchmark | 57.4% | — |
| CritPt | 1.7% | — |
| Chess Puzzles | — | 0% |
| LMCA | 28.6% | — |
| BIG-Bench Hard | — | 58.2% |
| Epoch Capabilities Index | — | 106.17 |
| HellaSwag | — | 80.7% |
| LAMBADA | — | 76.5% |
| PIQA | — | 80.8% |
| WinoGrande | — | 72.8% |
Math DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 38.5 (#137), Llama 2-13B: 31.1 (#229)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 2-13B |
|---|---|---|
| LMArena Math | 1402 | 1065 |
| GSM8K | — | 36.9% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Llama 2-13B: 28.1 (#249)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 2-13B |
|---|---|---|
| LMArena Expert | — | 1030 |
| ARC (AI2) Challenge | — | 60.3% |
| BoolQ | — | 82.4% |
| MMLU | — | 55.6% |
| OpenBookQA | — | 57% |
| TriviaQA | — | 79.6% |
Multimodal Not comparable
DeepSeek-V3.1-Terminus: —, Llama 2-13B: —
| Benchmark | DeepSeek-V3.1-Terminus | Llama 2-13B |
|---|---|---|
| ScienceQA | — | 55.8% |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.1 (#92), Llama 2-13B: 26.5 (#279)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 1407 | 1024 |
| LMArena Russian | 1436 | 1055 |
| LMArena Chinese | — | 1001 |
| LMArena French | — | 1044 |
| LMArena German | — | 1009 |
| LMArena Japanese | — | 894 |
| LMArena Korean | — | 953 |
| LMArena Spanish | — | 1087 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.0 (#106), Llama 2-13B: 53.3 (#287)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 1404 | 1045 |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.4 (#97), Llama 2-13B: 32.3 (#269)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | 1421 | 1064 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.0 (#92), Llama 2-13B: 29.8 (#289)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 2-13B |
|---|---|---|
| LMArena Text | 1419 | 1084 |
| LMArena Creative Writing | 1403 | 1047 |
| LMArena Multi-Turn | 1411 | 1050 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Llama 2-13B?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 29.6 on the Noometry Index.
Is DeepSeek-V3.1-Terminus or Llama 2-13B better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 30.9 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1-Terminus and Llama 2-13B share?
11 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Llama 2-13B has 32.