DeepSeek-R1 vs Mistral Small 3.2 vs Qwen3 235B-A22B

Mistral Small 3.2 is the better all-round choice, scoring 60/100 against Qwen3 235B-A22B (51) and DeepSeek-R1 (51). It leads on price and inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Mistral Small 3.2 is cheaper at $0.10 input / $0.30 output per million tokens (official Mistral API price). DeepSeek-R1 costs $0.70 input / $2.60 output per million tokens (median across 11 API providers); Qwen3 235B-A22B costs $0.70 input / $2.80 output per million tokens (official Alibaba API price). At a typical mix of three input tokens to one output token, that is $0.15 per million tokens for Mistral Small 3.2 versus $1.18 for DeepSeek-R1 (7.8× as much) and $1.23 for Qwen3 235B-A22B (8.2× as much).

Qwen3 235B-A22B scores higher on the Capabilities Index (ECI): Qwen3 235B-A22B 139.4 (#103 of 148), DeepSeek-R1 139.0 (#104 of 148) and Mistral Small 3.2 131.7 (#123 of 148). The confidence ranges of the top two overlap (135.2–140.8 vs 136.2–140.4), so treat the gap as small. On individual benchmarks: GPQA Diamond — DeepSeek-R1 71.7%, Qwen3 235B-A22B 70.7%, Mistral Small 3.2 49.1%.

There are no published SWE-bench Verified results for DeepSeek-R1, Mistral Small 3.2 and Qwen3 235B-A22B yet, so there is no like-for-like coding score. On overall capability, Qwen3 235B-A22B leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.

Qwen3 235B-A22B has the largest context window at 131,072 tokens, against 128,000 for DeepSeek-R1 and 128,000 for Mistral Small 3.2. Maximum output per response: DeepSeek-R1 up to 32,768, Mistral Small 3.2 up to 16,384, Qwen3 235B-A22B up to 16,384 tokens.

DeepSeek-R1 accepts text; Mistral Small 3.2 accepts text and images; Qwen3 235B-A22B accepts text. Mistral Small 3.2 handles the widest range of inputs.

Yes, all three publish their weights, so you can self-host them.

Mistral Small 3.2 is the newest, released Jun 20, 2025. Qwen3 235B-A22B came out Apr 28, 2025; DeepSeek-R1 came out Jan 20, 2025. Knowledge cutoff: DeepSeek-R1 Jul 2024, Mistral Small 3.2 Mar 2025, Qwen3 235B-A22B Apr 2025.

Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.