ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Qwen3.5 35B-A3BvsQwen3.5 397B-A17B

Qwen3.5 397B-A17B leads 4 of 4 shared benchmarks. Qwen3.5 35B-A3B is 2.3x cheaper per token. Both offer a 262K-token context window.

Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.

Shared benchmarks
0 – 4
Qwen3.5 397B-A17B leads
Cheaper per token
Qwen3.5 35B-A3B
2.3x cheaper, input + output
Larger context
Tie
both 262K tokens
Provider uptime (30d)
Qwen
textvision
Context
262K
Max out
Input /1M
$0.057
Output /1M
$0.459
Cached /1M
Scores
4 · 4 core
Qwen3.5 397B-A17B
Qwen · released 2026-02-15
textvision
Context
262K
Max out
Input /1M
$0.172
Output /1M
$1.03
Cached /1M
Scores
8 · 7 core
Quality

Benchmark matrix

BenchmarkQwen3.5 35B-A3BQwen3.5 397B-A17BΔEdge
Reported by both · 4
GPQA Diamond83.5% epoch88.4% -4.9 ptQwen3.5 397B-A17B
AIME 202693.3% matharena94.2% matharena-0.9 ptQwen3.5 397B-A17B
LMArena Elo1395.5 1438.3 -42.8Qwen3.5 397B-A17B
OTIS Mock AIME 2024-2025 (Epoch AI run)54.4% epoch88.9% epoch-34.5 ptQwen3.5 397B-A17B
Only Qwen3.5 35B-A3B reports · 0
Qwen3.5 35B-A3B reports nothing Qwen3.5 397B-A17B does not.
Only Qwen3.5 397B-A17B reports · 3
SWE-bench Verifiednot reported76.4%
MMLU-Pronot reported87.8%
FrontierMath Tiers 1-3 v2 (Epoch AI run)not reported29.5% epoch
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Qwen3.5 35B-A3B minus Qwen3.5 397B-A17B in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing

Side by side

SpecQwen3.5 35B-A3BQwen3.5 397B-A17BEdge
Context window262K tokens262K tokensTie
Max output
Input price / 1M$0.057 $0.172 Qwen3.5 35B-A3B
Output price / 1M$0.459 $1.03 Qwen3.5 35B-A3B
Cached input / 1M
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$0.516$1.2Qwen3.5 35B-A3B
Modalitiestext · visiontext · visionTie
Released2026-02-15
Cited benchmark scores48
Reliability

Qwen status

All providers
More matchups

Qwen3.5 35B-A3B vs …

More matchups

Qwen3.5 397B-A17B vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Qwen3.5 35B-A3B and Qwen3.5 397B-A17B on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.