Model comparison
Codestral vs Nemotron 3.5 Lightning
Nemotron 3.5 Lightning is the stronger model overall, scoring 39.3 to 30.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AI
NVIDIASummary
- The widest gap is in coding, where Nemotron 3.5 Lightning leads 39.6 to 26.9.
- Nemotron 3.5 Lightning is cheaper at $0.06 / $0.16 per million input/output tokens, against $0.30 / $0.90 for Codestral.
- Nemotron 3.5 Lightning accepts more context: 262K tokens versus 256K.
Side by side
| Codestral | Nemotron 3.5 Lightning | |
|---|---|---|
| Provider | Mistral AI | NVIDIA |
| Noometry Index | 30.1 | 39.3 |
| Released | 2024-05-29 | 2026-08-11 |
| Weights | Open | Open |
| Context window | 256K | 262K |
| Max output | 4K | 262K |
| Input $ / M tokens | $0.30 | $0.06 |
| Output $ / M tokens | $0.90 | $0.16 |
| Results tracked | 7 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3.5 Lightning leads
Codestral: 26.9 (#316), Nemotron 3.5 Lightning: 39.6 (#143)
| Benchmark | Codestral | Nemotron 3.5 Lightning |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1370 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning Nemotron 3.5 Lightning leads
Codestral: 19.1 (#244), Nemotron 3.5 Lightning: 25.7 (#128)
| Benchmark | Codestral | Nemotron 3.5 Lightning |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| LMArena Hard Prompts | — | 1335 |
Math Not comparable
Codestral: —, Nemotron 3.5 Lightning: 34.7 (#156)
| Benchmark | Codestral | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Math | — | 1355 |
Knowledge Not comparable
Codestral: —, Nemotron 3.5 Lightning: 36.9 (#154)
| Benchmark | Codestral | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Expert | — | 1354 |
Multilingual Not comparable
Codestral: —, Nemotron 3.5 Lightning: 44.0 (#175)
| Benchmark | Codestral | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Non-English | — | 1292 |
| LMArena Chinese | — | 1356 |
| LMArena French | — | 1369 |
| LMArena German | — | 1280 |
| LMArena Japanese | — | 1213 |
| LMArena Korean | — | 1233 |
| LMArena Russian | — | 1257 |
| LMArena Spanish | — | 1321 |
Instruction Following Not comparable
Codestral: —, Nemotron 3.5 Lightning: 69.8 (#166)
| Benchmark | Codestral | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Instruction Following | — | 1317 |
Long Context Not comparable
Codestral: —, Nemotron 3.5 Lightning: 39.9 (#160)
| Benchmark | Codestral | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Longer Query | — | 1312 |
Writing & Preference Not comparable
Codestral: —, Nemotron 3.5 Lightning: 48.5 (#198)
| Benchmark | Codestral | Nemotron 3.5 Lightning |
|---|---|---|
| LMArena Text | — | 1324 |
| LMArena Creative Writing | — | 1254 |
| EQ-Bench Creative Writing | — | 1280 |
| LMArena Multi-Turn | — | 1327 |
Frequently asked questions
Is Codestral better than Nemotron 3.5 Lightning?
Nemotron 3.5 Lightning is the stronger model overall, scoring 39.3 to 30.1 on the Noometry Index.
Which is cheaper, Codestral or Nemotron 3.5 Lightning?
Nemotron 3.5 Lightning is cheaper. It lists at $0.06 per million input tokens and $0.16 per million output tokens; Codestral lists at $0.30 and $0.90.
Is Codestral or Nemotron 3.5 Lightning better for coding?
Nemotron 3.5 Lightning scores higher on coding benchmarks: 39.6 versus 26.9 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3.5 Lightning does, with 262K tokens against 256K.
How many benchmarks do Codestral and Nemotron 3.5 Lightning share?
0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Nemotron 3.5 Lightning has 18.