Alibaba / Qwen, released Nov 12, 2024

Qwen2.5-Coder-32B-Instructprice, context, benchmarks and release details

Provisional: not enough results to rank yet Open weights 90% confidence, 3 of 5 expected sources in

39.6

SI Score

#127 of 142 ranked models

Input, per 1M tokens: not yet reported
Output, per 1M tokens: not yet reported
Context window: 131K
Max output: 8.2K
Released: Nov 12, 2024

How the score breaks down

Coding 19.9

Math —

Preference 53.7

Reasoning —

Weights: reasoning 30%, math 15%, coding 40%, preference 15%. Results use fixed 0–100 scales before averaging, and thin evidence is pulled toward 50. Method si-v3-retained-evidence-2, computed Oct 9, 2026, 06:15 UTC.

Around it on the leaderboard

125 Claude Haiku 3.5 40.8
126 Claude Haiku 3 39.9
127 Qwen2.5-Coder-32B-Instruct 39.6
128 Gemma 3 4B IT 39.2
129 GPT-5 Nano 39.1

Full leaderboard

Benchmark results

3 benchmarks, 4 results

Each row shows the best published result. Where a model was tested at several settings, such as reasoning effort, open the row to see each one. Hover or tap a value for its source.

Aider Polyglotcoding 16.4% 16.4

SWE-bench Verifiedcoding 38% 38.0 2 settings

About SWE-bench Verified

LMArena Textpreference 1230.0 elo 53.7

Normalization uses a fixed 0–100 scale for each unit, independent of other models. Compare evaluation conditions before reading a small gap as decisive. “Lab-reported” marks the provider's own published figure.

Details and sources

Open weights: Yes
License: not yet reported
Input modalities: text
First seen by SuperIndex: Oct 8, 2026
Coverage: 72% of expected source weight

Reported (3)

Aider polyglotOct 8, 2026
LMArena / ArenaOct 8, 2026
SWE-bench VerifiedOct 8, 2026

Awaiting (2)

Official model cards via models.dev7% of weight
LiveBench21% of weight

Confidence rises as pending sources publish. Some sources never cover some models, so confidence reaches 100% at 80% of expected weight.