Xentir Claude 3.5 Sonnet (October 2024) vs Qwen2.5-Max (25 Jan 2025)
Claude 3.5 Sonnet (October 2024) · Anthropic, released 2024-10-22
Qwen2.5-Max (25 Jan 2025) · Alibaba, released 2025-01-25
“Epoch AI, 'AI Benchmarking Hub'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks' [online resource].” · epoch.ai/benchmarks · Licensed CC BY 4.0 · data last verified 2026-09-09 · Methodology · Data Sources
Qwen2.5-Max (25 Jan 2025) leads on more of the 5 benchmarks where both are measured — Claude 3.5 Sonnet (October 2024) on 2, Qwen2.5-Max (25 Jan 2025) on 3. The remaining 4 of 9 tracked benchmarks cannot be compared: 1 has a result for only one of the two models, 3 for neither. Nothing on this page is estimated to fill those in.
Head-to-head
Measured on 5 of 9 tracked benchmarks for both models — Claude 3.5 Sonnet (October 2024) leads on 2, Qwen2.5-Max (25 Jan 2025) leads on 3.
| Benchmark | Claude 3.5 Sonnet (October 2024) | Qwen2.5-Max (25 Jan 2025) | Leads |
|---|---|---|---|
| Epoch Capabilities Index (ECI) | 133.6 | 132.5 | Claude 3.5 Sonnet (October 2024) |
| SWE-bench Verified | Not measured | Not measured | Not measured on both |
| GPQA Diamond | 0.553 | 0.561 | Qwen2.5-Max (25 Jan 2025) |
| MATH Level 5 | 0.569 | 0.672 | Qwen2.5-Max (25 Jan 2025) |
| OTIS Mock AIME 2024-2025 | 0.085 | 0.161 | Qwen2.5-Max (25 Jan 2025) |
| FrontierMath | 0.021 | 0.010 | Claude 3.5 Sonnet (October 2024) |
| FrontierMath Tier 4 | 0.000 | Not measured | Comparison unavailable — Qwen2.5-Max (25 Jan 2025) has no published result |
| SimpleQA Verified | Not measured | Not measured | Not measured on both |
| Chess Puzzles | Not measured | Not measured | Not measured on both |
What remains uncertain
- Qwen2.5-Max (25 Jan 2025) has no published result on FrontierMath Tier 4.
- 3 tracked benchmarks have no published result for either model.
A missing result means Xentir has not found one published by the source it cites, not that the model performs badly. See Data Sources.
Full profiles
Claude 3.5 Sonnet (October 2024) → · Qwen2.5-Max (25 Jan 2025) → · the full AI Model Rankings table