Qwen 3 32b
Qwen 3 32b is a 32b model. Supports switching between thinking and non thinking: trigger thinking with /think and /no_think anywhere in a prompt or system message to toggle chain-of-thought reasoning.
- Vision by description
- Native PDF input
Pricing
Auto routing · per 1M tokens- Input
- $0.08
- Output
- $0.28
- Cache read
- $0.08
Specifications
- Context window
- 41K
- Max output
- 32.8K
- Parameters
- 32B
Benchmarks
Benchmarks
Sourced from LMArena.
Arena Score
1346.8
Overall Rank
#228 / 421
Votes
3,926
Confidence Interval
1337.4 - 1356.3
Category Scores
Coding
#212 / 416
513 votes
1406.0
Math
#166 / 404
316 votes
1398.1
Longer Query
#222 / 399
504 votes
1355.1
Creative Writing
#238 / 419
616 votes
1303.7
Instruction Following
#232 / 421
858 votes
1331.0
Hard Prompts
#222 / 421
1,207 votes
1367.2
Additional Categories17
Industry Mathematical
#136 / 402
282 votes
1424.9
Expert
#189 / 371
236 votes
1397.7
German
#192 / 320
172 votes
1334.9
Industry Life And Physical And Social Science
#211 / 419
798 votes
1378.8
Industry Medicine And Healthcare
#211 / 391
212 votes
1379.2
Industry Software And It Services
#212 / 421
843 votes
1397.5
Hard Prompts English
#224 / 419
729 votes
1381.4
Exclude Ties
#228 / 421
2,544 votes
1306.7
English
#230 / 421
2,230 votes
1365.3
Non English
#231 / 421
1,696 votes
1323.3
Chinese
#232 / 395
187 votes
1361.9
Multi Turn
#233 / 419
590 votes
1336.9
Industry Business And Management And Financial Operations
#236 / 414
437 votes
1340.0
Russian
#236 / 385
412 votes
1327.8
Industry Writing And Literature And Language
#252 / 420
1,121 votes
1307.5
Industry Entertainment And Sports And Media
#260 / 419
704 votes
1285.3
Industry Legal And Government
#271 / 393
285 votes
1327.0
Published 2026-11-11 · Matched as Qwen3-32B · CC BY 4.0
LMArena DatasetLeaderboard results
| Benchmark | Score | Rank on NanoGPT |
|---|---|---|
Epoch AI Benchmarking Hub Epoch AI data, CC BY 4.0 · Updated Nov 13, 2026 | ||
Epoch Capabilities Index | 136.9 | #97 of 115 |
GPQA Diamond | 65.7% | #96 of 119 |
OTIS Mock AIME 2024–2025 | 66.9% | #91 of 121 |
Longform Writing | 40.5 | #82 of 97 |
EQ-Bench 3 | 1069 | #39 of 49 |
UGI Leaderboard UGI Leaderboard data, Apache-2.0 · Updated Oct 16, 2026 | ||
UGI Score | 31.0 | #106 of 149 |
UGI Willingness | 3.8 | #66 of 149 |
UGI Writing | 33.0 | #112 of 149 |
Filtered and ranked to models on NanoGPT.
Providers
Choose or restrict providers with the API. Provider-selection prices include the selection markup. Provider selection guide · Pricing API (JSON, USD per 1K tokens)
 | $0.08 | $0.28 | $0.08 | N/A | N/A |
| $0.08 | $0.28 | $0.08 | N/A | N/A |
| $0.084 | $0.294 | N/A | N/A | N/A | |
| $0.0998 | $0.299 | $0.0499 | N/A | N/A | |
| $0.147 | $0.599 | N/A | N/A | N/A | |
| $0.378 | $0.913 | N/A | N/A | N/A |
Batch rows for this model use normal routing and cost the same as standard API requests. Set provider in a row to choose a provider.