Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.
Qwen2.5-1M is clearly ahead on the aggregate, 73 to 23. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Qwen2.5-1M's sharpest advantage is in mathematics, where it averages 83.9 against 9.8. The single biggest benchmark swing on the page is AIME 2024, 87 to 9.8.
Pick Qwen2.5-1M if you want the stronger benchmark profile. GPT-4.1 nano only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.
Qwen2.5-1M
68.5
GPT-4.1 nano
65.2
Qwen2.5-1M
83.9
GPT-4.1 nano
9.8
Qwen2.5-1M
84
GPT-4.1 nano
83.2
Qwen2.5-1M is ahead overall, 73 to 23. The biggest single separator in this matchup is AIME 2024, where the scores are 87 and 9.8.
Qwen2.5-1M has the edge for knowledge tasks in this comparison, averaging 68.5 versus 65.2. Inside this category, GPQA is the benchmark that creates the most daylight between them.
Qwen2.5-1M has the edge for math in this comparison, averaging 83.9 versus 9.8. Inside this category, AIME 2024 is the benchmark that creates the most daylight between them.
Qwen2.5-1M has the edge for instruction following in this comparison, averaging 84 versus 83.2. Inside this category, IFEval is the benchmark that creates the most daylight between them.
Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.
Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.