Model comparison
Llama-3.3-70B-Instruct vs Mistral Nemo
Llama-3.3-70B-Instruct is the stronger model overall, scoring 30.6 to 26.4 on the Noometry Index.
Last verified . 6 shared benchmarks.
Meta
Mistral AISummary
- They share 6 benchmarks with published results for both. Llama-3.3-70B-Instruct scores higher in 3 categories and Mistral Nemo in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Llama-3.3-70B-Instruct leads 47.6 to 28.5.
- The biggest single-benchmark swing is MATH Level 5: 41.6% for Llama-3.3-70B-Instruct and 10.8% for Mistral Nemo.
- Both cost about the same: $0.10 input and $0.32 output per million tokens.
Side by side
| Llama-3.3-70B-Instruct | Mistral Nemo | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 30.6 | 26.4 |
| Released | 2024-12-06 | 2024-07-01 |
| Weights | Open | Open |
| Context window | 128K | 128K |
| Max output | 4K | 128K |
| Input $ / M tokens | $0.10 | $0.15 |
| Output $ / M tokens | $0.32 | $0.15 |
| Results tracked | 43 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama-3.3-70B-Instruct: 31.0 (#290), Mistral Nemo: —
| Benchmark | Llama-3.3-70B-Instruct | Mistral Nemo |
|---|---|---|
| SciCode | 26% | — |
| WeirdML | 14.4% | — |
| BigCodeBench Instruct | 46.9% | — |
| LiveBench Coding | 36.6% | — |
| LMArena Coding | 1268 | — |
| BigCodeBench Complete | 57.5% | — |
Agentic & Tool Use Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 25.8 (#105), Mistral Nemo: 23.5 (#125)
| Benchmark | Llama-3.3-70B-Instruct | Mistral Nemo |
|---|---|---|
| Berkeley Function Calling Leaderboard | 31.9% | 27.6% |
| BALROG | 23% | 17.6% |
Reasoning Mistral Nemo leads
Llama-3.3-70B-Instruct: 14.1 (#327), Mistral Nemo: 20.7 (#232)
| Benchmark | Llama-3.3-70B-Instruct | Mistral Nemo |
|---|---|---|
| DTBench | 59.5% | 48.6% |
| Epoch Capabilities Index | 127.33 | 118.68 |
| SimpleBench | 19.9% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | 50.8% | — |
| LMArena Hard Prompts | 1257 | — |
| LiveBench Data Analysis | 49.5% | — |
| LMCA | 17.5% | — |
| ForecastBench | 58.6 | — |
| LiveBench | 50.2% | — |
| PIQA | — | 83.5% |
Math Mistral Nemo leads
Llama-3.3-70B-Instruct: 15.3 (#298), Mistral Nemo: 25.5 (#268)
| Benchmark | Llama-3.3-70B-Instruct | Mistral Nemo |
|---|---|---|
| MATH Level 5 | 41.6% | 10.8% |
| OTIS Mock AIME 2024-2025 | 5.1% | — |
| LiveBench Math | 42.2% | — |
| LMArena Math | 1267 | — |
| GSM8K | — | 84.2% |
Knowledge Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 30.6 (#226), Mistral Nemo: 12.3 (#298)
| Benchmark | Llama-3.3-70B-Instruct | Mistral Nemo |
|---|---|---|
| GPQA Diamond | 47.4% | 29.9% |
| Confabulations | 22.8% | — |
| Vectara Hallucination Rate | 4.1% | — |
| LMArena Expert | 1225 | — |
| BoolQ | — | 82.5% |
| MMLU | 86.3% | — |
Multilingual Not comparable
Llama-3.3-70B-Instruct: 39.9 (#220), Mistral Nemo: —
| Benchmark | Llama-3.3-70B-Instruct | Mistral Nemo |
|---|---|---|
| LMArena Non-English | 1236 | — |
| LMArena Chinese | 1217 | — |
| LMArena French | 1281 | — |
| LMArena German | 1251 | — |
| LMArena Japanese | 1150 | — |
| LMArena Korean | 1143 | — |
| LMArena Russian | 1252 | — |
| LMArena Spanish | 1270 | — |
Instruction Following Not comparable
Llama-3.3-70B-Instruct: 71.1 (#157), Mistral Nemo: —
| Benchmark | Llama-3.3-70B-Instruct | Mistral Nemo |
|---|---|---|
| LiveBench Instruction Following | 82.7% | — |
| LMArena Instruction Following | 1242 | — |
Long Context Not comparable
Llama-3.3-70B-Instruct: 26.4 (#295), Mistral Nemo: —
| Benchmark | Llama-3.3-70B-Instruct | Mistral Nemo |
|---|---|---|
| Fiction.LiveBench | 33.3% | — |
| LMArena Longer Query | 1256 | — |
Writing & Preference Llama-3.3-70B-Instruct leads
Llama-3.3-70B-Instruct: 47.6 (#207), Mistral Nemo: 28.5 (#296)
| Benchmark | Llama-3.3-70B-Instruct | Mistral Nemo |
|---|---|---|
| LMArena Text | 1274 | — |
| LMArena Creative Writing | 1250 | — |
| EQ-Bench Creative Writing | — | 881 |
| LMArena Multi-Turn | 1280 | — |
| LiveBench Language | 39.2% | — |
Frequently asked questions
Is Llama-3.3-70B-Instruct better than Mistral Nemo?
Llama-3.3-70B-Instruct is the stronger model overall, scoring 30.6 to 26.4 on the Noometry Index.
Which is cheaper, Llama-3.3-70B-Instruct or Mistral Nemo?
Mistral Nemo is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; Llama-3.3-70B-Instruct lists at $0.10 and $0.32.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do Llama-3.3-70B-Instruct and Mistral Nemo share?
6 benchmarks have published results for both models. Llama-3.3-70B-Instruct has 43 scored results on Noometry and Mistral Nemo has 10.