DeepSeek-V3.1 vs Gemini 2.5 Flash vs Qwen3 235B-A22B
Gemini 2.5 Flash comes out ahead, 68 to 55 and 51 on our weighted score, though DeepSeek-V3.1 is 29% cheaper per token.
DeepSeekDeepSeek-V3.1
55/100- ECI139.9
- Price$0.385 / $1.25
- Context131K
- Our pick
GoogleGemini 2.5 Flash
68/100- ECI140.8
- Price$0.30 / $2.50
- Context1.05M
Alibaba (Qwen)Qwen3 235B-A22B
51/100- ECI139.4
- Price$0.70 / $2.80
- Context131K
Gemini 2.5 Flash is our pick
Gemini 2.5 Flash is the better all-round choice, scoring 68/100 against DeepSeek-V3.1 (55) and Qwen3 235B-A22B (51). It leads on inputs & features and context window. DeepSeek-V3.1 wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityGemini 2.5 FlashCapabilities Index (ECI): Gemini 2.5 Flash 140.8 · DeepSeek-V3.1 139.9 · Qwen3 235B-A22B 139.4
- Lowest priceDeepSeek-V3.1DeepSeek-V3.1 $0.601 · Gemini 2.5 Flash $0.85 · Qwen3 235B-A22B $1.23 per 1M tokens (3:1 blend)
- Longest contextGemini 2.5 FlashGemini 2.5 Flash 1,048,576 · DeepSeek-V3.1 131,072 · Qwen3 235B-A22B 131,072 tokens
- Widest inputsGemini 2.5 FlashDeepSeek-V3.1: Text · Gemini 2.5 Flash: Text, Images, PDFs, Audio, Video · Qwen3 235B-A22B: Text
- Self-hostingDeepSeek-V3.1 and Qwen3 235B-A22BPublishes downloadable weights (MIT License)
| Measure | Weight | DeepSeek-V3.1 | Gemini 2.5 Flash | Qwen3 235B-A22B |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 65 | 67 | 65 |
| Price | 25% | 60 | 53 | 46 |
| Inputs & features | 15% | 35 | 100 | 35 |
| Context window | 10% | 24 | 61 | 24 |
| Overall | 100% | 55/100 | 68/100 | 51/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | DeepSeek-V3.1DeepSeek | Gemini 2.5 FlashGoogle | Qwen3 235B-A22BAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 139.9 | 140.8 (best) | 139.4 |
| ECI rank | #100 of 148 | #97 of 148 (best) | #103 of 148 |
| GPQA DiamondGraduate-level science questions | — | — | 70.7% |
| Price per million tokens | |||
| Input | $0.385 | $0.30 (best) | $0.70 |
| Output | $1.25 (best) | $2.50 | $2.80 |
| Cached input | — | $0.03 | — |
| Blended (3:1) | $0.601 (best) | $0.85 | $1.23 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 8 providers | Official Google API | Official Alibaba API |
| Limits | |||
| Context window | 131,072 tokens | 1,048,576 tokens (best) | 131,072 tokens |
| Max output | 8,192 tokens | 65,536 tokens (best) | 16,384 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | Yes | No |
| Audio | No | Yes | No |
| Video | No | Yes | No |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | OpenMIT License | Proprietary | Open |
| API model ID | — | gemini-2.5-flash | qwen3-235b-a22b |
| API providers | 8 | 22 (best) | 7 |
| Released | Aug 21, 2025 | Jun 17, 2025 | Apr 28, 2025 |
| Knowledge cutoff | — | Jan 2025 | Apr 2025 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- DeepSeek-V3.1$6.35
- Gemini 2.5 Flash$8.00
- Qwen3 235B-A22B$12.60
Which should you choose?
Which is better: DeepSeek-V3.1, Gemini 2.5 Flash or Qwen3 235B-A22B?
Gemini 2.5 Flash is the better all-round choice, scoring 68/100 against DeepSeek-V3.1 (55) and Qwen3 235B-A22B (51). It leads on inputs & features and context window. DeepSeek-V3.1 wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, DeepSeek-V3.1, Gemini 2.5 Flash or Qwen3 235B-A22B?
DeepSeek-V3.1 is cheaper at $0.385 input / $1.25 output per million tokens (median across 8 API providers). Gemini 2.5 Flash costs $0.30 input / $2.50 output per million tokens (official Google API price); 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 $0.601 per million tokens for DeepSeek-V3.1 versus $0.85 for Gemini 2.5 Flash (1.4× as much) and $1.23 for Qwen3 235B-A22B (2× as much).
Which scores higher on benchmarks?
Gemini 2.5 Flash scores higher on the Capabilities Index (ECI): Gemini 2.5 Flash 140.8 (#97 of 148), DeepSeek-V3.1 139.9 (#100 of 148) and Qwen3 235B-A22B 139.4 (#103 of 148). The confidence ranges of the top two overlap (138.5–142.3 vs 136.1–143.3), so treat the gap as small.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek-V3.1, Gemini 2.5 Flash and Qwen3 235B-A22B yet, so there is no like-for-like coding score. On overall capability, Gemini 2.5 Flash leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.
Which has the bigger context window?
Gemini 2.5 Flash has the largest context window at 1,048,576 tokens, against 131,072 for DeepSeek-V3.1 and 131,072 for Qwen3 235B-A22B. Maximum output per response: DeepSeek-V3.1 up to 8,192, Gemini 2.5 Flash up to 65,536, Qwen3 235B-A22B up to 16,384 tokens.
Which can read images, PDFs, audio or video?
DeepSeek-V3.1 accepts text; Gemini 2.5 Flash accepts text, images, PDFs, audio and video; Qwen3 235B-A22B accepts text. Gemini 2.5 Flash handles the widest range of inputs.
Are any of these open source?
DeepSeek-V3.1 and Qwen3 235B-A22B publishes its weights (MIT License) and can be self-hosted; Gemini 2.5 Flash is proprietary.
Which is newer?
DeepSeek-V3.1 is the newest, released Aug 21, 2025. Gemini 2.5 Flash came out Jun 17, 2025; Qwen3 235B-A22B came out Apr 28, 2025. Knowledge cutoff: Gemini 2.5 Flash Jan 2025, Qwen3 235B-A22B Apr 2025.
How do you decide the winner?
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.
