Mistral Medium 3.5 Benchmark Details
Mistral Medium 3.5 currently shows benchmark results led by Terminal Bench Hard (86 / 244, score 33.30), ECI (90 / 167, score 141.42), τ³-Banking (112 / 167, score 15.10). This page also compares it with 3 competitor models and 2 predecessor or same-series models, including performance and pricing views when available.
Benchmark Results
Benchmark Results
Memory & Persistence
2 evaluationsCapability Indices
3 evaluationsService Workflows
2 evaluationsLegal
3 evaluationsFinance
2 evaluationsCode Generation & Editing
1 evaluationsClinical Workflows
2 evaluationsCompetitor Comparison
Benchmark scores for Mistral Medium 3.5 compared against top models in its class
12 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | Mistral Medium 3.5Current | Qwen3.6-27B | GLM-5.2 | Gemma 4 31B |
|---|---|---|---|---|
33.30Thinking Enabled ｜ Tools | 34.80Thinking Enabled ｜ Tools | 50.80Thinking Level · High ｜ Tools | 36.40Thinking Enabled ｜ Tools | |
32.05Thinking Level · High | 82.17Thinking Enabled | 72.34Thinking Level · High | -- | |
141.42Thinking Level · High | 146.47Thinking Level · High | 151.76Thinking Level · High | -- | |
17.95Thinking Level · High ｜ Tools | -- | 53.12Thinking Level · High ｜ Tools | -- | |
64.90Thinking Enabled | 74.60Thinking Enabled | -- | 76.90Thinking Level · High | |
39.58Thinking Enabled | 42.80Thinking Enabled | 51.20Thinking Level · High | 45.50Thinking Enabled | |
15.10Thinking Enabled ｜ Tools | 16.70Thinking Enabled ｜ Tools | 37.11Thinking Level · Extra High ｜ Tools | 14.80Thinking Enabled ｜ Tools | |
69.10Thinking Enabled ｜ Tools | 82.30Thinking Enabled ｜ Tools | 90.97Thinking Level · High ｜ Tools | 47.23Thinking Enabled ｜ Tools | |
0.42Thinking Level · High ｜ Tools | -- | 7.08Thinking Level · High ｜ Tools | -- | |
9.13Thinking Level · High ｜ Tools | -- | 31.25Thinking Level · High ｜ Tools | -- | |
11.19Thinking Level · High ｜ Tools | -- | 61.53Thinking Level · High ｜ Tools | -- | |
32.10Thinking Level · High ｜ Tools | -- | 49.70Thinking Level · High ｜ Tools | -- |
Standard API Pricing: Mistral Medium 3.5 vs. Peer Models
Shows standard text input and output pricing side by side for each model. If extended-context pricing exists, the chart keeps the base rate and explains the threshold below.
Source: DataLearnerAI. Standard text prices shown here use the default supplier. · USD / 1M tokens
| Model | Supplier | Standard input | Standard output | Base price applies to |
|---|---|---|---|---|
Mistral Medium 3.5 | MistralAI | $1.5 / 1M tokens | $7.5 / 1M tokens | — |
GLM-5.2 | 智谱AI | $1.4 / 1M tokens | $4.4 / 1M tokens | — |
Version History
How each version of the Mistral Medium 3.5 series stacks up on benchmark tests
5 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.· Click a row to view its trend chart.
| Benchmark | Mistral Medium 3.5Current | Mistral Large 3 | Devstral Medium |
|---|---|---|---|
33.30Thinking Enabled ｜ Tools | 15.90Standard Mode ｜ Tools | 9.10Standard Mode ｜ Tools | |
64.90Thinking Enabled | 55.70Standard Mode | -- | |
39.58Thinking Enabled | 36.60Standard Mode | -- | |
15.10Thinking Enabled ｜ Tools | 5.80Standard Mode ｜ Tools | -- | |
2.80Thinking Enabled | 1.20Standard Mode | -- |
Single-Benchmark Version Trend
Viewing: Terminal Bench Hard · Agentic Development
Standard API Pricing Across the Mistral Medium 3.5 Series
Shows standard text input and output pricing side by side for each model. If extended-context pricing exists, the chart keeps the base rate and explains the threshold below.
Source: DataLearnerAI. Standard text prices shown here use the default supplier. · USD / 1M tokens
| Model | Supplier | Standard input | Standard output | Base price applies to |
|---|---|---|---|---|
Mistral Medium 3.5 | MistralAI | $1.5 / 1M tokens | $7.5 / 1M tokens | — |
Mistral Large 3 | MistralAI | $0.5 / 1M tokens | $1.5 / 1M tokens | — |
Devstral Medium | MistralAI | $0.4 / 1M tokens | $2 / 1M tokens | — |