Mistral AI, open weights
Mistral Medium 3.5
Mistral Medium 3.5 by Mistral AI ranks 152nd of 354 ranked models on the Noometry Index as of October 2026, with a score of 40.2. Its strongest category is multimodal, where it ranks 65th. API pricing starts at $1.50 per million input tokens and $7.50 per million output tokens, with a 262K-token context window.
Last verified
Specifications
- Noometry rank
- #152 of 354
- Index score
- 40.2
- Evidence
- Confirmed 22 results
- Provider
Mistral AI- Released
- Unknown
- Weights
- Open weights
- Reasoning
- Yes
- Context window
- 262K
- Max output
- 210K
- Input price
- $1.50 / M
- Output price
- $7.50 / M
- Blended price
- $3 / M
- Output speed
- 50 tokens/s Kagi
- Value
- #169 of 219
- Knowledge cutoff
- Unknown
- Input
- text, image, file
Category scores
Each category score combines every public result we have in that category.
- Coding 36.0
- Reasoning 17.3
- Math 39.1
- Knowledge 40.0
- Multimodal 38.3
- Multilingual 51.9
- Instruction Following 74.6
- Long Context 43.2
- Writing & Preference 58.5
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 36.0 | #213 | 2 |
| Reasoning | 17.3 | #295 | 3 |
| Math | 39.1 | #113 | 1 |
| Knowledge | 40.0 | #126 | 1 |
| Multimodal | 38.3 | #65 | 1 |
| Multilingual | 51.9 | #100 | 1 |
| Instruction Following | 74.6 | #90 | 1 |
| Long Context | 43.2 | #103 | 1 |
| Writing & Preference | 58.5 | #117 | 4 |
Strengths and weaknesses
Categories where Mistral Medium 3.5 places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Instruction Following | 74.6 | +3.3 | #90 of 305, top 30% |
| Multilingual | 51.9 | +4.5 | #100 of 297, top 34% |
| Math | 39.1 | +2.6 | #113 of 327, top 35% |
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Reasoning | 17.3 | −6.3 | #295 of 350, top 85% |
| Coding | 36.0 | −2.7 | #213 of 340, top 63% |
| Multimodal | 38.3 | −0.2 | #65 of 128, top 51% |
Closest competitors
The models ranked just above and below Mistral Medium 3.5. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Granite 4.2 8B | #148 | 40.5 | $0.11 | — | Compare |
| Step 3 | #149 | 40.5 | — | 7 | Compare |
| MiniMax M1 | #150 | 40.3 | $0.96 | — | Compare |
| Nvidia Llama 3.3 Nemotron Super 49b v1.5 | #151 | 40.3 | $0.40 | — | Compare |
| Nemotron 3 Super | #153 | 40.1 | $0.17 | — | Compare |
| Llama 3.3 Nemotron 49b Super v1 | #154 | 40.1 | — | — | Compare |
| Nemotron 3.5 Lightning | #155 | 40.0 | $0.0875 | — | Compare |
| Qwen3.7 Flash | #156 | 39.9 | $0.055 | — | Compare |
Sponsored placements are available on pages like this one. Advertise on Noometry
Benchmark results
Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.
Coding
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena WebDev | 1264 | #99 of 113, top 88% | LMArena | 2026-10-08 | |
| LMArena Coding | 1461 | #70 of 294, top 24% | LMArena | 2026-10-08 |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Kagi LLM Benchmark | 41.4% | #75 of 99, top 76% | Kagi LLM Benchmark | ||
| NYT Connections (extended) | 12.9% | #85 of 91, top 94% | high | Lech Mazur benchmarks | |
| LMArena Hard Prompts | 1436 | #84 of 297, top 29% | LMArena | 2026-10-08 | |
| Epoch Capabilities Index | 141.35 | #103 of 213, top 49% | Epoch AI | 2026-04-28 |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Math | 1431 | #83 of 285, top 30% | LMArena | 2026-10-08 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Expert | 1432 | #93 of 273, top 35% | LMArena | 2026-10-08 |
Multimodal
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Vision | 1223 | #70 of 122, top 58% | LMArena | 2026-10-09 |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1404 | #100 of 297, top 34% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1442 | #109 of 285, top 39% | LMArena | 2026-10-08 | |
| LMArena French | 1448 | #73 of 223, top 33% | LMArena | 2026-10-08 | |
| LMArena German | 1451 | #43 of 231, top 19% | LMArena | 2026-10-08 | |
| LMArena Korean | 1385 | #71 of 213, top 34% | LMArena | 2026-10-08 | |
| LMArena Russian | 1395 | #111 of 283, top 40% | LMArena | 2026-10-08 | |
| LMArena Spanish | 1409 | #101 of 226, top 45% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Instruction Following | 1415 | #79 of 298, top 27% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1415 | #98 of 291, top 34% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1421 | #90 of 297, top 31% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1374 | #107 of 295, top 37% | LMArena | 2026-10-08 | |
| EQ-Bench 4 | 993 | #28 of 28, top 100% | EQ-Bench | ||
| LMArena Multi-Turn | 1423 | #93 of 295, top 32% | LMArena | 2026-10-08 |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| openrouter | $1.50 | $7.50 | — | 2026-10-10 |
Compare Mistral Medium 3.5
- Mistral Medium 3.5 vs Nvidia Llama 3.3 Nemotron Super 49b v1.5
- Mistral Medium 3.5 vs Nemotron 3 Super
- Mistral Medium 3.5 vs MiniMax M1
- Mistral Medium 3.5 vs Llama 3.3 Nemotron 49b Super v1
- Mistral Medium 3.5 vs Step 3
- Mistral Medium 3.5 vs Nemotron 3.5 Lightning
- Mistral Medium 3.5 vs GPT-6 Astra
- Mistral Medium 3.5 vs Claude Fable 5.1
- Mistral Medium 3.5 vs Gemini 3.8 Flash
- Mistral Medium 3.5 vs Kimi K3
- Mistral Medium 3.5 vs Grok 4.6
- Mistral Medium 3.5 vs Qwen3.8 Max
- Mistral Medium 3.5 vs GLM-5.3
- Mistral Medium 3.5 vs Muse Spark 1.3
Other Mistral AI models
- Mistral Large 443.1
- Mistral Large 339.1
- Mistral Medium36.3
- Magistral Medium35.2
- Devstral Small 250534.3
- Mistral Small33.4
- Pixtral Large32.2
- Mistral Large31.9
Frequently asked questions
How good is Mistral Medium 3.5?
Mistral Medium 3.5 by Mistral AI ranks 152nd of 354 ranked models on the Noometry Index as of October 2026, with a score of 40.2. Its strongest category is multimodal, where it ranks 65th. API pricing starts at $1.50 per million input tokens and $7.50 per million output tokens, with a 262K-token context window.
How much does Mistral Medium 3.5 cost?
Mistral Medium 3.5 costs $1.50 per million input tokens and $7.50 per million output tokens on openrouter.
What is Mistral Medium 3.5's context window?
Mistral Medium 3.5 accepts up to 262K tokens of input and can write up to 210K tokens in one response.
Is Mistral Medium 3.5 open source?
Yes. Mistral Medium 3.5's weights are downloadable; check the license for commercial terms.
How fast is Mistral Medium 3.5?
Mistral Medium 3.5 generated about 50 output tokens per second in the Kagi LLM Benchmark's timed runs. Speed varies by provider, load and reasoning effort.
What are Mistral Medium 3.5's strengths and weaknesses?
Relative to other ranked models, Mistral Medium 3.5 places best in instruction following, multilingual, math and lowest in reasoning, coding, multimodal.
What is Mistral Medium 3.5 best at?
Its best category is multimodal, where it ranks 65th on Noometry.