Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | 1.5B/7B/72B | 397B |
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 4k | 1M |
| API pricingUSD per 1M tokens · lower wins · base tier | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | — | $0.40International (Singapore) |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | — | $2.40 |
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | — | $0.26Alibaba |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | — | $1.56Alibaba |
| — | $130Alibaba | |
| These models have no shared benchmark scores. | ||
MATHReasoning — accuracy on the original competition mathematics test set | 85.9% | — |
GSM8KGrade-school math — Grade-school maths word problems that take a few steps of arithmetic to work through. It separated the models of 2022 and 2023 sharply, then saturated. One caveat on the historical numbers: OpenAI included part of the GSM8K training set in GPT-4's pre-training mix, so GPT-4's score is not a clean few-shot result. Higher is better. | 95.9% | — |
| Overview | ||
| Company | Qwen | Qwen |
| Release date | Sep 19 2024 | Feb 16 2026 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Qwen2.5-MathvsClaude Fable 5.2Qwen3.5-PlusvsClaude Fable 5.2Qwen2.5-MathvsGPT-6.2 AstraQwen3.5-PlusvsGPT-6.2 AstraQwen2.5-MathvsGemini 4 NeonQwen3.5-PlusvsGemini 4 NeonQwen2.5-MathvsMuse EmberQwen3.5-PlusvsMuse EmberQwen2.5-MathvsGrok 4.7Qwen3.5-PlusvsGrok 4.7Qwen2.5-MathvsDeepSeek-V4.1-Flash-1017Qwen3.5-PlusvsDeepSeek-V4.1-Flash-1017Frequently asked questions
Qwen2.5-Math and Qwen3.5-Plus don't publish scores on any of the same benchmarks, so there's no direct head-to-head comparison. Only Qwen3.5-Plus has a verified first-party price for an available API: $0.40 per million input tokens and $2.40 per million output tokens. No currently available pay-as-you-go API rate is tracked for Qwen2.5-Math. The listed Qwen3.5-Plus rates use the “International (Singapore)” pricing scope. Qwen2.5-Math shipped 515 days before Qwen3.5-Plus, so benchmark comparisons should account for the intervening progress.
Qwen2.5-Math has 1.5B/7B/72B parameters, while Qwen3.5-Plus has 397B. Context windows are 4k (Qwen2.5-Math) vs 1M (Qwen3.5-Plus). Qwen2.5-Math is open weight, while Qwen3.5-Plus is closed.
Direct benchmark comparisons are unavailable — Qwen2.5-Math and Qwen3.5-Plus don't publish scores on any of the same benchmarks.