Model comparison
Codestral vs Llama-3.3-70B-Instruct
Codestral and Llama-3.3-70B-Instruct score almost the same on the Noometry Index (30.6 vs 30.6), so choose on price, context window or the category you care about most.
Last verified . 2 shared benchmarks.
Mistral AI
MetaSummary
- They share 2 benchmarks with published results for both. Codestral scores higher in 1 category and Llama-3.3-70B-Instruct in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Codestral leads 19.8 to 14.1.
- The biggest single-benchmark swing is BigCodeBench Instruct: 41.8% for Codestral and 46.9% for Llama-3.3-70B-Instruct.
- Llama-3.3-70B-Instruct is cheaper at $0.10 / $0.32 per million input/output tokens, against $0.30 / $0.90 for Codestral.
- Codestral accepts more context: 256K tokens versus 128K.
- Llama-3.3-70B-Instruct has downloadable open weights; the other is API-only.
Side by side
| Codestral | Llama-3.3-70B-Instruct | |
|---|---|---|
| Provider | Mistral AI | Meta |
| Noometry Index | 30.6 | 30.6 |
| Released | 2024-05-29 | 2024-12-06 |
| Weights | Proprietary | Open |
| Context window | 256K | 128K |
| Max output | 8K | 4K |
| Input $ / M tokens | $0.30 | $0.10 |
| Output $ / M tokens | $0.90 | $0.32 |
| Results tracked | 7 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama-3.3-70B-Instruct leads
Codestral: 27.3 (#321), Llama-3.3-70B-Instruct: 31.0 (#290)
| Benchmark | Codestral | Llama-3.3-70B-Instruct |
|---|---|---|
| BigCodeBench Instruct | 41.8% | 46.9% |
| BigCodeBench Complete | 52.5% | 57.5% |
| Aider Polyglot | 11.1% | — |
| SciCode | — | 26% |
| WeirdML | — | 14.4% |
| LiveBench Coding | — | 36.6% |
| LMArena Coding | — | 1268 |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Agentic & Tool Use Not comparable
Codestral: —, Llama-3.3-70B-Instruct: 25.8 (#105)
| Benchmark | Codestral | Llama-3.3-70B-Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 31.9% |
| BALROG | — | 23% |
Reasoning Codestral leads
Codestral: 19.8 (#251), Llama-3.3-70B-Instruct: 14.1 (#327)
| Benchmark | Codestral | Llama-3.3-70B-Instruct |
|---|---|---|
| SimpleBench | — | 19.9% |
| Kagi LLM Benchmark | 32.5% | — |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 50.8% |
| LMArena Hard Prompts | — | 1257 |
| DTBench | — | 59.5% |
| LiveBench Data Analysis | — | 49.5% |
| LMCA | — | 17.5% |
| Epoch Capabilities Index | — | 127.33 |
| ForecastBench | — | 58.6 |
| LiveBench | — | 50.2% |
Math Not comparable
Codestral: —, Llama-3.3-70B-Instruct: 15.3 (#298)
| Benchmark | Codestral | Llama-3.3-70B-Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 5.1% |
| LiveBench Math | — | 42.2% |
| LMArena Math | — | 1267 |
| MATH Level 5 | — | 41.6% |
Knowledge Not comparable
Codestral: —, Llama-3.3-70B-Instruct: 30.6 (#226)
| Benchmark | Codestral | Llama-3.3-70B-Instruct |
|---|---|---|
| GPQA Diamond | — | 47.4% |
| Confabulations | — | 22.8% |
| Vectara Hallucination Rate | — | 4.1% |
| LMArena Expert | — | 1225 |
| MMLU | — | 86.3% |
Multilingual Not comparable
Codestral: —, Llama-3.3-70B-Instruct: 39.9 (#220)
| Benchmark | Codestral | Llama-3.3-70B-Instruct |
|---|---|---|
| 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
Codestral: —, Llama-3.3-70B-Instruct: 71.1 (#157)
| Benchmark | Codestral | Llama-3.3-70B-Instruct |
|---|---|---|
| LiveBench Instruction Following | — | 82.7% |
| LMArena Instruction Following | — | 1242 |
Long Context Not comparable
Codestral: —, Llama-3.3-70B-Instruct: 26.4 (#295)
| Benchmark | Codestral | Llama-3.3-70B-Instruct |
|---|---|---|
| Fiction.LiveBench | — | 33.3% |
| LMArena Longer Query | — | 1256 |
Writing & Preference Not comparable
Codestral: —, Llama-3.3-70B-Instruct: 47.6 (#207)
| Benchmark | Codestral | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Text | — | 1274 |
| LMArena Creative Writing | — | 1250 |
| LMArena Multi-Turn | — | 1280 |
| LiveBench Language | — | 39.2% |
Frequently asked questions
Is Codestral better than Llama-3.3-70B-Instruct?
Codestral and Llama-3.3-70B-Instruct score almost the same on the Noometry Index (30.6 vs 30.6), so choose on price, context window or the category you care about most.
Which is cheaper, Codestral or Llama-3.3-70B-Instruct?
Llama-3.3-70B-Instruct is cheaper. It lists at $0.10 per million input tokens and $0.32 per million output tokens; Codestral lists at $0.30 and $0.90.
Is Codestral or Llama-3.3-70B-Instruct better for coding?
Llama-3.3-70B-Instruct scores higher on coding benchmarks: 31.0 versus 27.3 in the Noometry coding category.
Which has the bigger context window?
Codestral does, with 256K tokens against 128K.
How many benchmarks do Codestral and Llama-3.3-70B-Instruct share?
2 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Llama-3.3-70B-Instruct has 43.