Model comparison
DeepSeek-R1 vs Llama 3-8B
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 25.5 on the Noometry Index.
Last verified . 22 shared benchmarks.
DeepSeek
MetaSummary
- They share 22 benchmarks with published results for both. DeepSeek-R1 scores higher in 8 categories and Llama 3-8B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-R1 leads 44.5 to 7.8.
- The biggest single-benchmark swing is MATH Level 5: 96.6% for DeepSeek-R1 and 6.1% for Llama 3-8B.
- Llama 3-8B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-R1 | Llama 3-8B | |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 42.3 | 25.5 |
| Released | 2025-01-20 | 2024-04-18 |
| Weights | Proprietary | Open |
| Context window | 164K | — |
| Max output | 64K | — |
| Input $ / M tokens | $0.50 | — |
| Output $ / M tokens | $2.15 | — |
| Results tracked | 52 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-R1 leads
DeepSeek-R1: 46.3 (#68), Llama 3-8B: 31.0 (#289)
| Benchmark | DeepSeek-R1 | Llama 3-8B |
|---|---|---|
| LMArena Coding | 1427 | 1152 |
| Aider Polyglot | 71.4% | — |
| SciCode | 35.7% | — |
| WeirdML | 41.6% | — |
| BigCodeBench Instruct | — | 31.9% |
| LiveBench Coding | 66.7% | — |
| BigCodeBench Complete | — | 36.9% |
| ALE-Bench | 804.12 | — |
| AlgoTune | 1.7 | — |
| HumanEval+ | — | 56.7% |
| MBPP+ | — | 54.8% |
Agentic & Tool Use Not comparable
DeepSeek-R1: 30.7 (#75), Llama 3-8B: —
| Benchmark | DeepSeek-R1 | Llama 3-8B |
|---|---|---|
| DeepResearch Bench | 35.1% | — |
| BALROG | 34.9% | — |
| METR Time Horizons | 53.8% | — |
Reasoning DeepSeek-R1 leads
DeepSeek-R1: 18.6 (#278), Llama 3-8B: 14.3 (#326)
| Benchmark | DeepSeek-R1 | Llama 3-8B |
|---|---|---|
| LMArena Hard Prompts | 1416 | 1133 |
| Epoch Capabilities Index | 141.29 | 116.45 |
| ForecastBench | 60 | 58.6 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 40.8% | — |
| Kagi LLM Benchmark | 69.4% | — |
| ARC-AGI-1 | 21.2% | — |
| CritPt | 1.1% | — |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | 83.2% | — |
| DTBench | — | 43.9% |
| LiveBench Data Analysis | 69.8% | — |
| Adversarial NLI | — | 57.3% |
| LiveBench | 71.6% | — |
| WinoGrande | — | 75.7% |
Math DeepSeek-R1 leads
DeepSeek-R1: 43.8 (#79), Llama 3-8B: 8.8 (#323)
| Benchmark | DeepSeek-R1 | Llama 3-8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.4% | 1.9% |
| LMArena Math | 1400 | 1151 |
| MATH Level 5 | 96.6% | 6.1% |
| Omni-MATH | 42.4% | — |
| LiveBench Math | 80.7% | — |
Knowledge DeepSeek-R1 leads
DeepSeek-R1: 44.5 (#87), Llama 3-8B: 7.8 (#308)
| Benchmark | DeepSeek-R1 | Llama 3-8B |
|---|---|---|
| GPQA Diamond | 76.3% | 26.1% |
| LMArena Expert | 1394 | 1113 |
| MMLU-Pro | 79.3% | — |
| Confabulations | 12.7% | — |
| Vectara Hallucination Rate | 11.3% | — |
| GPQA (HELM) | 66.6% | — |
| ARC (AI2) Challenge | — | 82.8% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 82.6% |
| TriviaQA | — | 67.7% |
Multilingual DeepSeek-R1 leads
DeepSeek-R1: 52.4 (#85), Llama 3-8B: 30.8 (#261)
| Benchmark | DeepSeek-R1 | Llama 3-8B |
|---|---|---|
| LMArena Non-English | 1412 | 1098 |
| LMArena Chinese | 1442 | 1076 |
| LMArena French | 1417 | 1159 |
| LMArena German | 1404 | 1104 |
| LMArena Japanese | 1391 | 967 |
| LMArena Korean | 1360 | 1004 |
| LMArena Russian | 1423 | 1109 |
| LMArena Spanish | 1411 | 1173 |
Instruction Following DeepSeek-R1 leads
DeepSeek-R1: 72.0 (#143), Llama 3-8B: 58.4 (#260)
| Benchmark | DeepSeek-R1 | Llama 3-8B |
|---|---|---|
| LMArena Instruction Following | 1382 | 1127 |
| LiveBench Instruction Following | 80.5% | — |
| IFEval | 78.4% | — |
Long Context DeepSeek-R1 leads
DeepSeek-R1: 45.4 (#36), Llama 3-8B: 34.2 (#251)
| Benchmark | DeepSeek-R1 | Llama 3-8B |
|---|---|---|
| LMArena Longer Query | 1391 | 1128 |
| Fiction.LiveBench | 75% | — |
Writing & Preference DeepSeek-R1 leads
DeepSeek-R1: 61.4 (#88), Llama 3-8B: 37.5 (#256)
| Benchmark | DeepSeek-R1 | Llama 3-8B |
|---|---|---|
| LMArena Text | 1428 | 1166 |
| LMArena Creative Writing | 1405 | 1150 |
| LMArena Multi-Turn | 1405 | 1152 |
| Short-Story Creative Writing | 83% | — |
| EQ-Bench Creative Writing | 1500 | — |
| WildBench | 82.8% | — |
| LiveBench Language | 48.5% | — |
Frequently asked questions
Is DeepSeek-R1 better than Llama 3-8B?
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 25.5 on the Noometry Index.
Is DeepSeek-R1 or Llama 3-8B better for coding?
DeepSeek-R1 scores higher on coding benchmarks: 46.3 versus 31.0 in the Noometry coding category.
How many benchmarks do DeepSeek-R1 and Llama 3-8B share?
22 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and Llama 3-8B has 34.