Qwen2.5-Coder-32B-Instruct: Price, Context, Benchmarks, and Release Details
39.6
SI Score (method si-v2-absolute-shrinkage-1)
#107 of 115 ranked
75% confidence 75 percent, Medium confidence — 1 of 3 expected sources in
Coverage 60% of expected source weight · 100% confidence at 80% coverage
Pillar breakdown
Coding (weight 40 percent) 19.9
Math (weight 15 percent) —
Preference (weight 15 percent) 53.7
Reasoning (weight 30 percent) —
Pillar weights: reasoning 30% · math 15% · coding 40% · preference 15%. Benchmark results use fixed 0–100 scales before averaging; incomplete evidence is shrunk toward 50.
Facts
- Input price / 1M
- not yet reported
- Output price / 1M
- not yet reported
- Context window
- 131Kmodels.devPublished source fact
Retrieved Oct 8, 2026 · MIT
Open source ↗ - Max output
- 8.2Kmodels.devPublished source fact
Retrieved Oct 8, 2026 · MIT
Open source ↗ - Released
- Nov 12, 2024models.devPublished source fact
Retrieved Oct 8, 2026 · MIT
Open source ↗ - Open weights
- Yesmodels.devPublished source fact
Retrieved Oct 8, 2026 · MIT
Open source ↗ - License
- not yet reported
- Input modalities
- textmodels.devPublished source fact
Retrieved Oct 8, 2026 · MIT
Open source ↗
Benchmark results
4 results| Benchmark | Raw result | Normalized (0–100) | Pillar |
|---|---|---|---|
| aider polyglot | 16.4%Aider polyglotPublished source fact [variant] Aider polyglot; 225 cases; 2 attemptsPublished Dec 26, 2024
Retrieved Oct 8, 2026 · Apache-2.0 Open source ↗ | 16.4 | coding |
| lmarena text | 1230.0 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 2, 2026
Retrieved Oct 8, 2026 · CC-BY-4.0 Open source ↗ | 53.7 | preference |
| swe bench verified | 9%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] mini-SWE-agent; 1.0.0Published Aug 3, 2025
Retrieved Oct 8, 2026 · factual citation Open source ↗ | 9.0 | coding |
| swe bench verified | 38%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] Skywork-SWE-32BPublished Jun 16, 2025
Retrieved Oct 8, 2026 · factual citation Open source ↗ | 38.0 | coding |
Normalization uses fixed absolute 0–100 scales for each unit, independently of other models that have a result on each benchmark. Coverage and evidence breadth still affect the composite; compare the evaluation conditions before reading a small score gap as decisive. “lab-reported” marks the provider's own published figure.
Sources: in and pending
in Reported (1)
- LMArena / Arena · arrived Oct 8, 2026
pending Awaiting (2)
- Official model cards via models.dev · carries 10% of expected weight
- LiveBench · carries 30% of expected weight
The confidence % rises as pending sources publish. Some sources never cover some models — that is why 100% confidence arrives at 80% of expected weight, not at full coverage.