Mistral Medium 3.5 128B
MistralOpen weightsReasoningProvisionalReleased Apr 29, 2026
Overall score
33.6
Rank 168 of 222 · 19.3–48.0
Context window
256K
256,000 tokens
Price per 1M tokens
$1.50 in · $7.50 out
Source: BenchLM
Blended price
$3.00
3:1 input:output tokens
Output speed
—
Not measured yet
Category scores
Scores per capability area with the model's rank among ranked models in that category.
- 1Instruction following#5284.0
- 2Reasoning72.6
- 3Coding66.0
- 4Multimodal60.1
- 5Knowledge34.1
Benchmark results (3)
As reported in system cards, papers and public evaluations. Position compares this model with every other model reporting the same benchmark.
Agentic & tool use
| Gert Labs | 39.10 | #40 of 52 |
| τ³-bench results | 91.4 | #2 of 23 |
Coding
| SWE-bench Verified | 77.6 | #30 of 98 |
Pricing by source
USD per 1M tokens.
| Source | Input | Output | Cached in |
|---|---|---|---|
| List price (BenchLM) | $1.50 | $7.50 | — |
Mistral's April 29, 2026 launch post lists Mistral Medium 3.5 API pricing at $1.50 input / $7.50 output per million tokens and describes the 128B dense model as open weights under a modified MIT license.
Open weights
From the Hugging Face repository.
- Parameters
- 128B
- Licence
- other
- Downloads (30 days)
- 75.1K
- Repository
- mistralai/Mistral-Medium-3.5-128B ↗
Speed
Measured by us through OpenRouter (median of trials).
Not available on OpenRouter, so we cannot measure it yet.
Related models
Same family
- Mistral Medium 328.8
Similar score
- Mercury 233.7 · $0.38
- Kimi K233.5 · $1.07
- Mistral Large 333.5 · $0.75
- GPT-OSS 20B33.3 · $0.036
- Mercury 2.534.0 · $0.068