Model comparison
DeepSeek-V3.1-Terminus vs Llama 4 Scout
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 27.4 on the Noometry Index. Llama 4 Scout costs 3.2× less per token, which makes it the better buy when DeepSeek-V3.1-Terminus's lead doesn't matter for your workload.
Last verified . 15 shared benchmarks.
DeepSeek
MetaSummary
- They share 15 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 7 categories and Llama 4 Scout in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.3 to 37.1.
- The biggest single-benchmark swing is SciCode: 40.6% for DeepSeek-V3.1-Terminus and 17% for Llama 4 Scout.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.30 / $1 for DeepSeek-V3.1-Terminus.
- DeepSeek-V3.1-Terminus accepts more context: 164K tokens versus 128K.
Side by side
| DeepSeek-V3.1-Terminus | Llama 4 Scout | |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 42.6 | 27.4 |
| Released | 2025-09-22 | 2025-04-05 |
| Weights | Open | Open |
| Context window | 164K | 128K |
| Max output | 66K | 4K |
| Input $ / M tokens | $0.30 | $0.10 |
| Output $ / M tokens | $1 | $0.30 |
| Results tracked | 16 | 43 |
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: 41.5 (#114), Llama 4 Scout: 19.9 (#334)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 4 Scout |
|---|---|---|
| SciCode | 40.6% | 17% |
| LMArena Coding | 1426 | 1286 |
| SWE-bench Verified (bash only) | — | 9.1% |
| BigCodeBench Complete | — | 43.1% |
| ALE-Bench | 745.17 | — |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, Llama 4 Scout: 24.4 (#109)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 4 Scout |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.1% |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 25.7 (#126), Llama 4 Scout: 9.2 (#339)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 4 Scout |
|---|---|---|
| Kagi LLM Benchmark | 57.4% | 36.9% |
| CritPt | 1.7% | 0% |
| LMArena Hard Prompts | 1427 | 1266 |
| DTBench | 81.3% | 57.9% |
| LMCA | 28.6% | 12% |
| ARC-AGI-2 | — | 0% |
| ARC-AGI-1 | — | 0.5% |
| Epoch Capabilities Index | — | 129.64 |
| ForecastBench | — | 57.5 |
Math DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 35.7 (#138), Llama 4 Scout: 18.4 (#280)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 4 Scout |
|---|---|---|
| LMArena Math | 1402 | 1286 |
| OTIS Mock AIME 2024-2025 | — | 7.8% |
| Omni-MATH | — | 37.3% |
| MATH Level 5 | — | 62.3% |
| FrontierMath (Feb 2025 set) | — | 0% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Llama 4 Scout: 31.8 (#208)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 4 Scout |
|---|---|---|
| GPQA Diamond | — | 51.8% |
| MMLU-Pro | — | 74.2% |
| Vectara Hallucination Rate | — | 7.7% |
| GPQA (HELM) | — | 50.7% |
| LMArena Expert | — | 1236 |
Multimodal Not comparable
DeepSeek-V3.1-Terminus: —, Llama 4 Scout: 31.6 (#98)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 4 Scout |
|---|---|---|
| LMArena Vision | — | 1118 |
| SpatialViz-Bench | — | 34.2% |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.3 (#87), Llama 4 Scout: 41.3 (#207)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 4 Scout |
|---|---|---|
| LMArena Non-English | 1407 | 1253 |
| LMArena Russian | 1434 | 1263 |
| LMArena Chinese | — | 1256 |
| LMArena French | — | 1283 |
| LMArena German | — | 1274 |
| LMArena Japanese | — | 1209 |
| LMArena Korean | — | 1207 |
| LMArena Spanish | — | 1277 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.4 (#96), Llama 4 Scout: 66.0 (#212)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 4 Scout |
|---|---|---|
| LMArena Instruction Following | 1406 | 1248 |
| IFEval | — | 81.8% |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.5 (#88), Llama 4 Scout: 27.5 (#289)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 4 Scout |
|---|---|---|
| LMArena Longer Query | 1426 | 1265 |
| Fiction.LiveBench | — | 36% |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.3 (#87), Llama 4 Scout: 37.1 (#256)
| Benchmark | DeepSeek-V3.1-Terminus | Llama 4 Scout |
|---|---|---|
| LMArena Text | 1420 | 1279 |
| LMArena Creative Writing | 1404 | 1249 |
| LMArena Multi-Turn | 1411 | 1281 |
| EQ-Bench Creative Writing | — | 783 |
| WildBench | — | 78% |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Llama 4 Scout?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 27.4 on the Noometry Index. Llama 4 Scout costs 3.2× less per token, which makes it the better buy when DeepSeek-V3.1-Terminus's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-V3.1-Terminus or Llama 4 Scout?
Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; DeepSeek-V3.1-Terminus lists at $0.30 and $1.
Is DeepSeek-V3.1-Terminus or Llama 4 Scout better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 19.9 in the Noometry coding category.
Which has the bigger context window?
DeepSeek-V3.1-Terminus does, with 164K tokens against 128K.
How many benchmarks do DeepSeek-V3.1-Terminus and Llama 4 Scout share?
15 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Llama 4 Scout has 43.