Compare · ModelsLive · 2 picked · head to head
Mistral Medium 3.5 vs Qwen3.6 35B A3B
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Qwen3.6 35B A3B wins on 12/17 benchmarks
Qwen3.6 35B A3B wins 12 of 17 shared benchmarks. Leads in speed · general.
Category leads
speed·Qwen3.6 35B A3Bgeneral·Qwen3.6 35B A3Bcoding·Mistral Medium 3.5
Hype vs Reality
Attention vs performance
Mistral Medium 3.5
#250 by perf·no signal
Qwen3.6 35B A3B
#178 by perf·#2 by attention
Best value
Qwen3.6 35B A3B
11.0x better value than Mistral Medium 3.5
Mistral Medium 3.5
6.6 pts/$
$4.50/M
Qwen3.6 35B A3B
72.3 pts/$
$0.57/M
Vendor risk
Who is behind the model
Mistral AI
$14.0B·Tier 1
Alibaba (Qwen)
$293.0B·Tier 1
Head to head
17 benchmarks · 2 models
Mistral Medium 3.5Qwen3.6 35B A3B
Artificial Analysis · Agentic Index
Qwen3.6 35B A3B leads by +2.4
Artificial Analysis Agentic Index · a composite score measuring how well a model performs in agentic workflows · multi-step tool use, planning, error recovery, and autonomous task completion. Aggregates results from multiple agentic benchmarks including SWE-bench, tool-use tests, and planning evaluations. The canonical single-number metric for "how good is this model as an agent?"
Mistral Medium 3.5
19.0
Qwen3.6 35B A3B
21.4
Artificial Analysis · Coding Index
Mistral Medium 3.5 leads by +5.0
Artificial Analysis Coding Index · a composite score that aggregates performance across multiple coding benchmarks into a single index. Tracks code generation quality, debugging ability, multi-language competence, and real-world software engineering tasks. Used by Artificial Analysis to rank model coding capability in a normalized, comparable format. Useful for developers choosing between models for coding-heavy workloads.
Mistral Medium 3.5
46.9
Qwen3.6 35B A3B
41.9
Artificial Analysis · CritPt
Qwen3.6 35B A3B leads by +0.3
Mistral Medium 3.5
0.0
Qwen3.6 35B A3B
0.3
Artificial Analysis · GDPval
Qwen3.6 35B A3B leads by +6.6
Mistral Medium 3.5
12.4
Qwen3.6 35B A3B
19.0
Artificial Analysis · GPQA Diamond
Qwen3.6 35B A3B leads by +9.3
Mistral Medium 3.5
74.8
Qwen3.6 35B A3B
84.1
Artificial Analysis · Humanity's Last Exam
Qwen3.6 35B A3B leads by +8.4
Mistral Medium 3.5
13.8
Qwen3.6 35B A3B
22.2
Artificial Analysis · IFBench
Mistral Medium 3.5 leads by +4.4
Mistral Medium 3.5
68.8
Qwen3.6 35B A3B
64.4
Artificial Analysis · Long Context Reasoning
Qwen3.6 35B A3B leads by +2.4
Mistral Medium 3.5
69.3
Qwen3.6 35B A3B
71.7
Artificial Analysis · MMMU Pro
Qwen3.6 35B A3B leads by +10.1
Mistral Medium 3.5
64.9
Qwen3.6 35B A3B
75.0
Artificial Analysis · Quality Index
Qwen3.6 35B A3B leads by +4.0
Mistral Medium 3.5
14.2
Qwen3.6 35B A3B
18.2
Artificial Analysis · SciCode
Mistral Medium 3.5 leads by +3.6
Mistral Medium 3.5
40.2
Qwen3.6 35B A3B
36.6
Artificial Analysis · tau2-Bench Telecom
Qwen3.6 35B A3B leads by +1.1
Mistral Medium 3.5
94.2
Qwen3.6 35B A3B
95.3
Artificial Analysis · Terminal-Bench Hard
Qwen3.6 35B A3B leads by +1.5
Mistral Medium 3.5
33.3
Qwen3.6 35B A3B
34.8
Dtbench
Mistral Medium 3.5 leads by +2.7
Mistral Medium 3.5
59.1
Qwen3.6 35B A3B
56.5
Lmca
Qwen3.6 35B A3B leads by +4.3
Mistral Medium 3.5
30.7
Qwen3.6 35B A3B
34.9
Surface Evolver Bench
Qwen3.6 35B A3B leads by +17.5
Mistral Medium 3.5
26.9
Qwen3.6 35B A3B
44.4
WeirdML
Mistral Medium 3.5 leads by +9.2
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
Mistral Medium 3.5
43.7
Qwen3.6 35B A3B
34.5
Full benchmark table
| Benchmark | Mistral Medium 3.5 | Qwen3.6 35B A3B |
|---|---|---|
Artificial Analysis · Agentic Index Artificial Analysis Agentic Index · a composite score measuring how well a model performs in agentic workflows · multi-step tool use, planning, error recovery, and autonomous task completion. Aggregates results from multiple agentic benchmarks including SWE-bench, tool-use tests, and planning evaluations. The canonical single-number metric for "how good is this model as an agent?" | 19.0 | 21.4 |
Artificial Analysis · Coding Index Artificial Analysis Coding Index · a composite score that aggregates performance across multiple coding benchmarks into a single index. Tracks code generation quality, debugging ability, multi-language competence, and real-world software engineering tasks. Used by Artificial Analysis to rank model coding capability in a normalized, comparable format. Useful for developers choosing between models for coding-heavy workloads. | 46.9 | 41.9 |
Artificial Analysis · CritPt | 0.0 | 0.3 |
Artificial Analysis · GDPval | 12.4 | 19.0 |
Artificial Analysis · GPQA Diamond | 74.8 | 84.1 |
Artificial Analysis · Humanity's Last Exam | 13.8 | 22.2 |
Artificial Analysis · IFBench | 68.8 | 64.4 |
Artificial Analysis · Long Context Reasoning | 69.3 | 71.7 |
Artificial Analysis · MMMU Pro | 64.9 | 75.0 |
Artificial Analysis · Quality Index | 14.2 | 18.2 |
Artificial Analysis · SciCode | 40.2 | 36.6 |
Artificial Analysis · tau2-Bench Telecom | 94.2 | 95.3 |
Artificial Analysis · Terminal-Bench Hard | 33.3 | 34.8 |
Dtbench | 59.1 | 56.5 |
Lmca | 30.7 | 34.9 |
Surface Evolver Bench | 26.9 | 44.4 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 43.7 | 34.5 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $1.50 | $7.50 | 262K tokens (~131 books) | $30.00 | |
| $0.15 | $1.00 | 262K tokens (~131 books) | $3.63 |