Skip to main content

Claude 3.5 Sonnet vs Qwen3 235B-A22B

SpecClaude 3.5 SonnetQwen3 235B-A22B
Respan Index16.4 (#150)16.7 (#149)
Blended price per 1M--
Context window200K262K
Input / output per 1M--
Max output8K-
Inputtext, visiontext
Released2024-10-222025-04-29

Respan Index by category

Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.

CategoryClaude 3.5 SonnetQwen3 235B-A22B
Coding7.3 Claude 3.5 Sonnet4.2 Qwen3 235B-A22B
Agents13.1 Claude 3.5 Sonnet12.5* Qwen3 235B-A22B
Reasoning16.9 Claude 3.5 Sonnet20.3 Qwen3 235B-A22B
Knowledge & language9.3* Claude 3.5 Sonnet11.1* Qwen3 235B-A22B
Human preference40.7 Claude 3.5 Sonnet42.0 Qwen3 235B-A22B

* Estimated: no published scores in that category. How the Respan Index works

Benchmarks both report

Qwen3 235B-A22B leads on 4 of the 5 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkClaude 3.5 SonnetQwen3 235B-A22B
LMArena Elo13741375
GPQA Diamond55.3%70.7%
MATH Level 5 (Epoch AI)56.9%68.9%
WeirdML (Håvard Tveit Ihle)40%37.3%
AIME 20253.3%80.8%

FAQ

Is Claude 3.5 Sonnet better than Qwen3 235B-A22B?

Qwen3 235B-A22B scores 16.7 on the Respan Index (#149), ahead of Claude 3.5 Sonnet at 16.4 (#150). Qwen3 235B-A22B leads on 4 of the 5 benchmarks both report.

Which has the larger context window?

Claude 3.5 Sonnet accepts 200K tokens and Qwen3 235B-A22B 262K tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.