LLM Reference

Mistral Large 2 vs Qwen3.5-397B-A17B

Mistral Large 2 (2025) and Qwen3.5-397B-A17B (2026) are frontier reasoning models from MistralAI and Alibaba. Mistral Large 2 ships a 128k-token context window, while Qwen3.5-397B-A17B ships a 262k-token context window. On MMLU PRO, Qwen3.5-397B-A17B leads by 18.1 pts. On pricing, Qwen3.5-397B-A17B costs $0.39/1M 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.

Qwen3.5-397B-A17B is safer overall; choose Mistral Large 2 when vision-heavy evaluation matters.

Decision scorecard

Local evidence first
SignalMistral Large 2Qwen3.5-397B-A17B
Best formultimodal apps, tool-calling agents, and provider-routed productionreasoning-heavy apps, multimodal apps, and tool-calling agents
Decision fitCoding, RAG, and AgentsCoding, RAG, and Agents
Context window128k262k
Cheapest output$2.40/1M tokens$2.34/1M tokens
Provider routes4 tracked4 tracked
Shared benchmarks2 rowsMMLU PRO leader

Decision tradeoffs

Choose Mistral Large 2 when...
  • Local decision data tags Mistral Large 2 for Coding, RAG, and Agents.
Choose Qwen3.5-397B-A17B when...
  • Qwen3.5-397B-A17B holds a shared-benchmark lead on MMLU PRO, ahead by 18.1 points.
  • Qwen3.5-397B-A17B has the larger context window for long prompts, retrieval packs, or transcript analysis.
  • Qwen3.5-397B-A17B has the lower cheapest tracked output price at $2.34/1M tokens.
  • Qwen3.5-397B-A17B uniquely exposes Reasoning in local model data.
  • Local decision data tags Qwen3.5-397B-A17B for Coding, RAG, and Agents.

Monthly cost at traffic

Estimate token spend from the cheapest tracked input and output route or tier on this page.

Lower estimate Qwen3.5-397B-A17B

Mistral Large 2

$984

Cheapest tracked route/tier: AWS Bedrock

Qwen3.5-397B-A17B

$897

Cheapest tracked route/tier: OpenRouter

Estimated monthly gap: $87.00. Batch, cache, alternate speed tiers, and negotiated pricing are excluded from this local estimate.

Switch friction

Mistral Large 2 -> Qwen3.5-397B-A17B
  • Provider overlap exists on OpenRouter; start route-level A/B tests there.
  • Qwen3.5-397B-A17B is $0.06/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.
  • Qwen3.5-397B-A17B adds Reasoning in local capability data.
Qwen3.5-397B-A17B -> Mistral Large 2
  • Provider overlap exists on OpenRouter; start route-level A/B tests there.
  • Mistral Large 2 is $0.06/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.
  • Check replacement coverage for Reasoning before moving production traffic.

Specs

Specification
Released2025-11-252026-02-16
Context window128k262k
Parameters123B397B
Architecturedecoder onlyMoE
LicenseMistral LicenseApache 2.0(OSI)
OpennessOpen weightsOpen source
Commercial useNon-commercial onlyCommercial use allowed
Knowledge cutoff2025-07-

Pricing and availability

Pricing attributeMistral Large 2Qwen3.5-397B-A17B
Input price$0.48/1M tokens$0.39/1M tokens
Output price$2.40/1M tokens$2.34/1M tokens
Providers

Capabilities

CapabilityMistral Large 2Qwen3.5-397B-A17B
VisionYesYes
MultimodalYesYes
ReasoningNoYes
Function callingYesYes
Tool useYesYes
Structured outputsYesYes
Code executionNoNo
IDE integrationNoNo
Computer useNoNo
Parallel agentsNoNo

Benchmarks

BenchmarkMistral Large 2Qwen3.5-397B-A17B
MMLU PRO69.787.8
BFCL38.472.9

Deep dive

On shared benchmark coverage, MMLU PRO has Mistral Large 2 at 69.7 and Qwen3.5-397B-A17B at 87.8, with Qwen3.5-397B-A17B ahead by 18.1 points; BFCL has Mistral Large 2 at 38.4 and Qwen3.5-397B-A17B at 72.9, with Qwen3.5-397B-A17B ahead by 34.5 points. The largest visible gap is 34.5 points on BFCL, which matters most when that benchmark mirrors your workload. Treat isolated benchmark wins as directional, because provider routing, prompt style, and tool access can move real application results.

The capability footprint differs most on reasoning mode: Qwen3.5-397B-A17B. Both models share vision, multimodal input, function calling, and tool use, so the practical split is not just feature count. Use those differences to decide whether the page is about raw model quality, agentic coding support, multimodal ingestion, or predictable structured API behavior.

For cost, Mistral Large 2 lists $0.48/1M input and $2.40/1M output tokens on the cheapest tracked provider, while Qwen3.5-397B-A17B lists $0.39/1M input and $2.34/1M output tokens on the cheapest tracked provider. A 70/30 input-output blend puts Qwen3.5-397B-A17B lower by about $0.08 per million blended tokens. Availability is 4 providers versus 4, so concentration risk also matters.

Choose Mistral Large 2 when vision-heavy evaluation are central to the workload. Choose Qwen3.5-397B-A17B when reasoning depth, larger context windows, and lower input-token cost are more important. For production, rerun your own prompts through the exact provider, region, and tool stack you plan to ship.

FAQ

Which has a larger context window, Mistral Large 2 or Qwen3.5-397B-A17B?

Qwen3.5-397B-A17B supports 262k tokens, while Mistral Large 2 supports 128k tokens. That gap matters most for long documents, large codebases, retrieval-heavy agents, and conversations where earlier context must remain visible.

Which is cheaper, Mistral Large 2 or Qwen3.5-397B-A17B?

Qwen3.5-397B-A17B is cheaper on tracked token pricing. Mistral Large 2 costs $0.48/1M input and $2.40/1M output tokens. Qwen3.5-397B-A17B costs $0.39/1M input and $2.34/1M output tokens. Provider discounts or batch pricing can still change the final bill.

Is Mistral Large 2 or Qwen3.5-397B-A17B open source?

Mistral Large 2 is listed under Mistral License. Qwen3.5-397B-A17B is listed under Apache 2.0. License labels affect whether you can self-host, redistribute weights, or rely only on hosted APIs, so confirm the upstream license before deployment.

Which is better for vision, Mistral Large 2 or Qwen3.5-397B-A17B?

Both Mistral Large 2 and Qwen3.5-397B-A17B expose vision. The better choice depends on benchmark fit, context budget, pricing, and whether your provider route exposes the same capability surface. Use this as a quick comparison signal, then confirm the provider-specific limits before committing to production.

Which is better for multimodal input, Mistral Large 2 or Qwen3.5-397B-A17B?

Both Mistral Large 2 and Qwen3.5-397B-A17B expose multimodal input. The better choice depends on benchmark fit, context budget, pricing, and whether your provider route exposes the same capability surface. Use this as a quick comparison signal, then confirm the provider-specific limits before committing to production.

Where can I run Mistral Large 2 and Qwen3.5-397B-A17B?

Mistral Large 2 is available on OpenRouter, IBM watsonx, AWS Bedrock, and Mistral AI Studio. Qwen3.5-397B-A17B is available on OpenRouter, Together AI, Alibaba Cloud PAI-EAS, and Novita AI. Provider coverage can affect latency, region availability, compliance posture, and fallback options.

Continue comparing

Last reviewed: 2026-06-04. Data sourced from public model cards and provider documentation.