Mistral Large 2 vs Qwen3-235B-A22B
Mistral Large 2 (2025) and Qwen3-235B-A22B (2025) are compact production models from MistralAI and Alibaba. Both ship a 128k-token context window. On MMLU PRO, Qwen3-235B-A22B leads by 13.1 pts. On pricing, Qwen3-235B-A22B costs $0.09/1M input tokens versus $0.48/1M for the alternative. This comparison covers specs, pricing, API access, capabilities, benchmarks, input and output token costs, and production fit for coding and agent workloads.
Qwen3-235B-A22B is ~433% cheaper at $0.09/1M; pay for Mistral Large 2 only for vision-heavy evaluation.
Decision scorecard
Local evidence first| Signal | Mistral Large 2 | Qwen3-235B-A22B |
|---|---|---|
| Best for | multimodal apps, tool-calling agents, and provider-routed production | provider-routed production |
| Decision fit | Coding, RAG, and Agents | Coding, RAG, and Long context |
| Context window | 128k | 128k |
| Cheapest output | $2.40/1M tokens | $0.58/1M tokens |
| Provider routes | 3 tracked | 5 tracked |
| Shared benchmarks | 2 shared | MMLU PRO leader |
Decision tradeoffs
- Mistral Large 2 uniquely exposes Vision, Multimodal, and JSON / Tool use in local model data.
- Local decision data tags Mistral Large 2 for Coding, RAG, and Agents.
- Qwen3-235B-A22B holds a shared-benchmark lead on MMLU PRO, ahead by 13.1 points.
- Qwen3-235B-A22B has the lower cheapest tracked output price at $0.58/1M tokens.
- Qwen3-235B-A22B has broader tracked provider coverage for fallback and route flexibility.
- Local decision data tags Qwen3-235B-A22B for Coding, RAG, and Long context.
Monthly cost at traffic
Estimate token spend from the cheapest tracked input and output route or tier on this page.
Mistral Large 2
$984
Cheapest tracked route/tier: AWS Bedrock
Qwen3-235B-A22B
$217
Cheapest tracked route/tier: Novita AI
Estimated monthly gap: $767. Batch, cache, alternate speed tiers, and negotiated pricing are excluded from this local estimate.
Switch friction
- Provider overlap exists on AWS Bedrock; start route-level A/B tests there.
- Qwen3-235B-A22B is $1.82/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.
- Check replacement coverage for Vision, Multimodal, and JSON / Tool use before moving production traffic.
- Provider overlap exists on AWS Bedrock; start route-level A/B tests there.
- Mistral Large 2 is $1.82/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.
- Mistral Large 2 adds Vision, Multimodal, and JSON / Tool use in local capability data.
Specs
| Specification | ||
|---|---|---|
| Released | 2025-11-25 | 2025-04-29 |
| Context window | 128k | 128k |
| Parameters | 123B | 235B |
| Architecture | Decoder Only | Decoder Only |
| License | Mistral License | Apache 2.0OSI-approved |
| Openness | Open weights | Open source |
| Weights | Unknown | Unknown |
| Code | Unknown | Unknown |
| Commercial use | Commercial use: non-commercial | Commercial use: permitted |
| Knowledge cutoff | 2025-07 | - |
Pricing and availability
| Pricing attribute | Mistral Large 2 | Qwen3-235B-A22B |
|---|---|---|
| Input price | $0.48/1M tokens | $0.09/1M tokens |
| Output price | $2.40/1M tokens | $0.58/1M tokens |
| Providers |
Capabilities
| Capability | Mistral Large 2 | Qwen3-235B-A22B |
|---|---|---|
| Vision | Yes | No |
| Multimodal | Yes | No |
| Reasoning | No | No |
| JSON / Tool use | Yes | No |
| Structured outputs | Yes | Yes |
| Code execution | No | No |
| IDE integration | No | No |
| Computer use | No | No |
| Parallel agents | No | No |
Benchmarks
| Benchmark | Mistral Large 2 | Qwen3-235B-A22B |
|---|---|---|
| MMLU PRO | 69.7 | 82.8 |
| HumanEval | 84.8 | 92.7 |
Continue comparing
Popular comparisons for Mistral Large 2
Popular comparisons for Qwen3-235B-A22B
Last reviewed: 2026-06-29. Data sourced from public model cards and provider documentation.