Skip to content
ModelCap

Head-to-head comparison

Qwen2.5 72B Instruct vs Qwen3.5 397B A17B

Qwen2.5 72B Instruct (Qwen) and Qwen3.5 397B A17B (Qwen) compared on the ModelCap Index, API price, context window, provider availability, weight access and every public benchmark board they share. Figures are the same ones shown on the live rankings; nothing here is a hidden score.

Snapshot as of 23 September 2026

As of 23 September 2026, Qwen3.5 397B A17B holds the stronger ModelCap Index position (#41 vs #183); Qwen2.5 72B Instruct is 8.8× cheaper per output token ($0.40/1M vs $3.50/1M); Qwen3.5 397B A17B offers the longer context window (262K vs 33K tokens); and Qwen3.5 397B A17B ships open weights.

Which should you choose?

Choose Qwen2.5 72B Instruct if…

  • API cost matters — $0.40/1M output tokens against $3.50/1M, about 8.8× cheaper.
  • your workload is prompt-heavy — input tokens cost $0.36/1M against $0.55/1M.

Choose Qwen3.5 397B A17B if…

  • you want the stronger overall ModelCap Index position — #41 against #183 (70.2 vs 27.0 points).
  • you need the longer context window — 262K tokens against 33K.
  • you want to self-host: Qwen3.5 397B A17B ships open weights while Qwen2.5 72B Instruct is restricted license.
  • you want provider choice — 10 listed API providers against 2.
  • Arena coding is your yardstick — 1491 against 1355.
  • AA τ²-Bench Telecom is your yardstick — 95.6% against 34.5%.
  • AA Humanity's Last Exam is your yardstick — 29.0% against 3.6%.
  • you want the more recently listed model — Qwen3.5 397B A17B was listed 16 February 2026, Qwen2.5 72B Instruct 19 September 2024.

Qwen2.5 72B Instruct vs Qwen3.5 397B A17B: specs, pricing and context

Specification comparison of Qwen2.5 72B Instruct and Qwen3.5 397B A17B
FieldQwen2.5 72B InstructQwenQwen3.5 397B A17BQwen
ModelCap Index position#183#41
Index score27.070.2
EvidenceMeasuredMeasured
Input price / 1M tokens$0.36$0.55
Output price / 1M tokens$0.40$3.50
Context window33K tokens262K tokens
Max output tokens16K236K
API providers listed210
Weight accessRestricted licenseOpen weights
Input modalitiesTextText, Image, Video
First listed19 September 202416 February 2026
PublisherQwenQwen

Evidence: 2 public benchmark observations across 2 boards · 3 public benchmark observations across 3 boards. Prices are the lowest listed API offer per million tokens observed on the OpenRouter catalogue.

Benchmark scores: Qwen2.5 72B Instruct vs Qwen3.5 397B A17B

Public benchmark boards where Qwen2.5 72B Instruct or Qwen3.5 397B A17B has a published result
BoardQwen2.5 72B InstructQwen3.5 397B A17BLeads
Arena codingArena (LMArena)13551348–136314911486–1496Qwen3.5 397B A17B
AA Intelligence IndexArtificial Analysis—18.4intelligence-index:v4.3:reasoning-unspecifiedOnly one result
AA τ²-Bench TelecomArtificial Analysis34.5%tau2:telecom:dual-control:pass-at-1:3-repeats:source-model="Qwen2.5 Instruct 72B":reasoning=false95.6%tau2:telecom:dual-control:pass-at-1:3-repeats:source-model="Qwen3.5 397B A17B (Reasoning)":reasoning=trueQwen3.5 397B A17B
AA Humanity's Last ExamArtificial Analysis3.6%hle:may-2025:text-only-2158:no-tools:pass-at-1:source-model="Qwen2.5 Instruct 72B":reasoning=false29.0%hle:may-2025:text-only-2158:no-tools:pass-at-1:source-model="Qwen3.5 397B A17B (Reasoning)":reasoning=trueQwen3.5 397B A17B

Scores are the sources' own published figures for each model's best evaluated configuration; ModelCap never re-runs a benchmark.

Want a different pairing? Open the interactive comparison tool to swap either model for any current ranked language model.

Qwen2.5 72B Instruct vs Qwen3.5 397B A17B: common questions

Is Qwen2.5 72B Instruct better than Qwen3.5 397B A17B?

Qwen3.5 397B A17B ranks higher on the ModelCap Index as of 23 September 2026: #41 against #183. That is a capability ranking built from public benchmark evidence with published uncertainty; whether it is "better" for you also depends on price, context and where you can run it. Their published uncertainty intervals do not overlap, but the aggregate Index does not predict performance on every task; compare the relevant benchmark configurations before choosing.

Is Qwen2.5 72B Instruct cheaper than Qwen3.5 397B A17B?

Qwen2.5 72B Instruct is cheaper on output tokens: $0.40/1M against $3.50/1M. Input tokens are $0.36/1M for Qwen2.5 72B Instruct and $0.55/1M for Qwen3.5 397B A17B. Prices are the lowest listed API offer ModelCap observed, in USD per million tokens. For 1,000 requests with 2,000 input and 500 output tokens each (2M input + 0.5M output), the listed-rate estimate is $0.92 for Qwen2.5 72B Instruct versus $2.85 for Qwen3.5 397B A17B. Qwen2.5 72B Instruct costs 67.7% less in this scenario. This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the selected endpoint before budgeting.

Which has the bigger context window, Qwen2.5 72B Instruct or Qwen3.5 397B A17B?

Qwen3.5 397B A17B has the larger context window: 262K tokens against 33K.

Which is better for coding, Qwen2.5 72B Instruct or Qwen3.5 397B A17B?

Arena coding: Qwen2.5 72B Instruct 1355, Qwen3.5 397B A17B 1491 — Qwen3.5 397B A17B leads.

Are Qwen2.5 72B Instruct and Qwen3.5 397B A17B open-weight models?

Qwen2.5 72B Instruct: Restricted license. Qwen3.5 397B A17B: Open weights. Open weights mean the checkpoint can be downloaded and self-hosted under its licence; API-only models are available solely through hosted endpoints.

Where can I run Qwen2.5 72B Instruct and Qwen3.5 397B A17B?

ModelCap currently lists 2 API providers for Qwen2.5 72B Instruct and 10 for Qwen3.5 397B A17B, from the OpenRouter catalogue snapshot the site serves; each model page lists the providers and their prices.

How current is this Qwen2.5 72B Instruct vs Qwen3.5 397B A17B comparison?

Every figure comes from the sealed ModelCap dataset published 23 September 2026; the page re-renders within a minute of each data refresh, and the ModelCap Index positions are the same ones shown on the live rankings.

Explore further