Skip to content
ModelCap

Head-to-head comparison

Qwen3 30B A3B Instruct 2507 vs Qwen3.5-122B-A10B

Qwen3 30B A3B Instruct 2507 (Qwen) and Qwen3.5-122B-A10B (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 22 September 2026

As of 22 September 2026, Qwen3.5-122B-A10B holds the stronger ModelCap Index position (#73 vs #107); and Qwen3 30B A3B Instruct 2507 is 10.8× cheaper per output token ($0.193/1M vs $2.08/1M).

Which should you choose?

Choose Qwen3 30B A3B Instruct 2507 if…

  • API cost matters — $0.193/1M output tokens against $2.08/1M, about 10.8× cheaper.
  • your workload is prompt-heavy — input tokens cost $0.048/1M against $0.26/1M.

Choose Qwen3.5-122B-A10B if…

  • you want the stronger overall ModelCap Index position — #73 against #107 (60.8 vs 50.5 points).
  • Arena coding is your yardstick — 1459 against 1439.
  • you want the more recently listed model — Qwen3.5-122B-A10B was listed 25 February 2026, Qwen3 30B A3B Instruct 2507 29 July 2025.

Qwen3 30B A3B Instruct 2507 vs Qwen3.5-122B-A10B: specs, pricing and context

Specification comparison of Qwen3 30B A3B Instruct 2507 and Qwen3.5-122B-A10B
FieldQwen3 30B A3B Instruct 2507QwenQwen3.5-122B-A10BQwen
ModelCap Index position#107#73
Index score50.560.8
EvidenceMeasuredMeasured
Input price / 1M tokens$0.048$0.26
Output price / 1M tokens$0.193$2.08
Context window262K tokens262K tokens
Max output tokens32K66K
API providers listed55
Weight accessOpen weightsOpen weights
Input modalitiesTextText, Image, Video
First listed29 July 202525 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: Qwen3 30B A3B Instruct 2507 vs Qwen3.5-122B-A10B

Public benchmark boards where Qwen3 30B A3B Instruct 2507 or Qwen3.5-122B-A10B has a published result
BoardQwen3 30B A3B Instruct 2507Qwen3.5-122B-A10BLeads
Arena codingArena (LMArena)14391430–144814591452–1466Qwen3.5-122B-A10B
BFCL V4UC Berkeley (Gorilla)41.4Function calling—Only one result
AA Intelligence IndexArtificial Analysis—15.6intelligence-index:v4.3:reasoning-unspecifiedOnly one result
AA τ²-Bench TelecomArtificial Analysis—93.6%tau2:telecom:dual-control:pass-at-1:3-repeats:source-model="Qwen3.5 122B A10B (Reasoning)":reasoning=trueOnly one result
AA Humanity's Last ExamArtificial Analysis—25.2%hle:may-2025:text-only-2158:no-tools:pass-at-1:source-model="Qwen3.5 122B A10B (Reasoning)":reasoning=trueOnly one result

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.

Qwen3 30B A3B Instruct 2507 vs Qwen3.5-122B-A10B: common questions

Is Qwen3 30B A3B Instruct 2507 better than Qwen3.5-122B-A10B?

Qwen3.5-122B-A10B ranks higher on the ModelCap Index as of 22 September 2026: #73 against #107. 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 overlap, so the rank difference alone does not establish a reliable capability advantage for your workload.

Is Qwen3 30B A3B Instruct 2507 cheaper than Qwen3.5-122B-A10B?

Qwen3 30B A3B Instruct 2507 is cheaper on output tokens: $0.193/1M against $2.08/1M. Input tokens are $0.048/1M for Qwen3 30B A3B Instruct 2507 and $0.26/1M for Qwen3.5-122B-A10B. 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 $0.19 for Qwen3 30B A3B Instruct 2507 versus $1.56 for Qwen3.5-122B-A10B. Qwen3 30B A3B Instruct 2507 costs 87.6% 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, Qwen3 30B A3B Instruct 2507 or Qwen3.5-122B-A10B?

Both publish a 262K-token context window.

Which is better for coding, Qwen3 30B A3B Instruct 2507 or Qwen3.5-122B-A10B?

Arena coding: Qwen3 30B A3B Instruct 2507 1439, Qwen3.5-122B-A10B 1459 — Qwen3.5-122B-A10B leads.

Are Qwen3 30B A3B Instruct 2507 and Qwen3.5-122B-A10B open-weight models?

Qwen3 30B A3B Instruct 2507: Open weights. Qwen3.5-122B-A10B: 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 Qwen3 30B A3B Instruct 2507 and Qwen3.5-122B-A10B?

ModelCap currently lists 5 API providers for Qwen3 30B A3B Instruct 2507 and 5 for Qwen3.5-122B-A10B, from the OpenRouter catalogue snapshot the site serves; each model page lists the providers and their prices.

How current is this Qwen3 30B A3B Instruct 2507 vs Qwen3.5-122B-A10B comparison?

Every figure comes from the sealed ModelCap dataset published 22 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