ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

o3vsQwen3.5 35B-A3B

o3 and Qwen3.5 35B-A3B split their 2 shared benchmarks evenly. Qwen3.5 35B-A3B is 19.4x cheaper per token. Qwen3.5 35B-A3B has the larger context window (262K tokens).

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

Shared benchmarks
1 – 1
even split
Cheaper per token
Qwen3.5 35B-A3B
19.4x cheaper, input + output
Larger context
Qwen3.5 35B-A3B
262K tokens
Provider uptime (30d)
94.2446% · —
OpenAI · Qwen
o3
OpenAI · released 2025-04-16
textvision
Context
200K
Max out
100K
Input /1M
$2
Output /1M
$8
Cached /1M
$0.5
Scores
7 · 7 core
textvision
Context
262K
Max out
Input /1M
$0.057
Output /1M
$0.459
Cached /1M
Scores
4 · 4 core
Quality

Benchmark matrix

Benchmarko3Qwen3.5 35B-A3BΔEdge
Reported by both · 2
GPQA Diamond81.8% epoch83.5% epoch-1.7 ptQwen3.5 35B-A3B
OTIS Mock AIME 2024-2025 (Epoch AI run)84.4% epoch54.4% epoch+30 pto3
Only o3 reports · 5
SWE-bench Verified69.1% not reported
AIME 202589.2% matharenanot reported
FrontierMath Tiers 1-3 v2 (Epoch AI run)33.3% epochnot reported
SimpleQA Verified49.4% epochnot reported
SWE-bench Verified (Epoch AI run)62.3% epochnot reported
Only Qwen3.5 35B-A3B reports · 2
AIME 2026not reported93.3% matharena
LMArena Elonot reported1395.5
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 o3 minus Qwen3.5 35B-A3B 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

Speco3Qwen3.5 35B-A3BEdge
Context window200K tokens262K tokensQwen3.5 35B-A3B
Max output100K tokens
Input price / 1M$2 $0.057 Qwen3.5 35B-A3B
Output price / 1M$8 $0.459 Qwen3.5 35B-A3B
Cached input / 1M$0.5
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$10$0.516Qwen3.5 35B-A3B
Modalitiestext · visiontext · visionTie
Released2025-04-16
Cited benchmark scores74
Reliability

Provider status

All providers
More matchups

Qwen3.5 35B-A3B vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run o3 and Qwen3.5 35B-A3B on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.