Gemma 4 31B IT vs DeepSeek V4 Flash vs Qwen3.5 Flash
Qwen3.5 Flash comes out ahead, 75 to 71 and 69 on our weighted score.
GoogleGemma 4 31B IT
69/100- ECI142.8
- Price$0.14 / $0.40
- Context262K
DeepSeekDeepSeek V4 Flash
71/100- ECI146.1
- Price$0.14 / $0.28
- Context1M
- Our pick
Alibaba (Qwen)Qwen3.5 Flash
75/100- ECI144.0
- Price$0.10 / $0.40
- Context1M
Qwen3.5 Flash is our pick
Qwen3.5 Flash is the better all-round choice, scoring 75/100 against DeepSeek V4 Flash (71) and Gemma 4 31B IT (69). It leads on inputs & features. DeepSeek V4 Flash wins on capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityDeepSeek V4 FlashCapabilities Index (ECI): DeepSeek V4 Flash 146.1 · Qwen3.5 Flash 144.0 · Gemma 4 31B IT 142.8
- Lowest priceDeepSeek V4 Flash and Qwen3.5 FlashDeepSeek V4 Flash $0.175 · Qwen3.5 Flash $0.175 · Gemma 4 31B IT $0.205 per 1M tokens (3:1 blend)
- Longest contextDeepSeek V4 Flash and Qwen3.5 FlashDeepSeek V4 Flash 1,000,000 · Qwen3.5 Flash 1,000,000 · Gemma 4 31B IT 262,144 tokens
- Widest inputsQwen3.5 FlashGemma 4 31B IT: Text, Images · DeepSeek V4 Flash: Text · Qwen3.5 Flash: Text, Images, Video
- Self-hostingGemma 4 31B IT and DeepSeek V4 FlashPublishes downloadable weights
| Measure | Weight | Gemma 4 31B IT | DeepSeek V4 Flash | Qwen3.5 Flash |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 69 | 73 | 71 |
| Price | 25% | 83 | 86 | 86 |
| Inputs & features | 15% | 70 | 45 | 80 |
| Context window | 10% | 37 | 60 | 60 |
| Overall | 100% | 69/100 | 71/100 | 75/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Gemma 4 31B ITGoogle | DeepSeek V4 FlashDeepSeek | Qwen3.5 FlashAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 142.8 | 146.1 (best) | 144.0 |
| ECI rank | #86 of 148 | #71 of 148 (best) | #82 of 148 |
| GPQA DiamondGraduate-level science questions | 75.8% | — | 82.3% (best) |
| FrontierMath Tiers 1–3Research-level mathematics | — | — | 18.3% |
| OTIS Mock AIME 2024–2025Competition mathematics | 73.3% | — | 84.4% (best) |
| SimpleQA VerifiedShort factual questions | 10.4% | — | 20.3% (best) |
| Price per million tokens | |||
| Input | $0.14 | $0.14 | $0.10 (best) |
| Output | $0.40 | $0.28 (best) | $0.40 |
| Cached input | — | — | $0.01 |
| Blended (3:1) | $0.205 | $0.175 (best) | $0.175 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 30 providers | Median of 42 providers | Official Alibaba API |
| Limits | |||
| Context window | 262,144 tokens | 1,000,000 tokens (best) | 1,000,000 tokens (best) |
| Max output | 32,768 tokens | 384,000 tokens (best) | 65,536 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | Yes |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | Yes |
| Availability | |||
| Weights | Open | Open | Proprietary |
| API model ID | gemma-4-31b-it | — | qwen3.5-flash |
| API providers | 38 | 48 (best) | 8 |
| Released | Apr 2, 2026 | Apr 24, 2026 | Feb 23, 2026 |
| Knowledge cutoff | — | May 2025 | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Gemma 4 31B IT$2.20
- DeepSeek V4 Flash$1.96
- Qwen3.5 Flash$1.80
Which should you choose?
Which is better: Gemma 4 31B IT, DeepSeek V4 Flash or Qwen3.5 Flash?
Qwen3.5 Flash is the better all-round choice, scoring 75/100 against DeepSeek V4 Flash (71) and Gemma 4 31B IT (69). It leads on inputs & features. DeepSeek V4 Flash wins on capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, Gemma 4 31B IT, DeepSeek V4 Flash or Qwen3.5 Flash?
DeepSeek V4 Flash is cheaper at $0.14 input / $0.28 output per million tokens (median across 42 API providers). Qwen3.5 Flash costs $0.10 input / $0.40 output per million tokens (official Alibaba API price); Gemma 4 31B IT costs $0.14 input / $0.40 output per million tokens (median across 30 API providers). At a typical mix of three input tokens to one output token, that is $0.175 per million tokens for DeepSeek V4 Flash versus $0.175 for Qwen3.5 Flash (1× as much) and $0.205 for Gemma 4 31B IT (1.2× as much).
Which scores higher on benchmarks?
DeepSeek V4 Flash scores higher on the Capabilities Index (ECI): DeepSeek V4 Flash 146.1 (#71 of 148), Qwen3.5 Flash 144.0 (#82 of 148) and Gemma 4 31B IT 142.8 (#86 of 148). The confidence ranges of the top two overlap (143.6–147.9 vs 141.6–145.5), so treat the gap as small.
Which is better for coding?
There are no published SWE-bench Verified results for Gemma 4 31B IT, DeepSeek V4 Flash and Qwen3.5 Flash yet, so there is no like-for-like coding score. On overall capability, DeepSeek V4 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?
DeepSeek V4 Flash and Qwen3.5 Flash have the largest context windows (1,000,000 and 1,000,000 tokens), against 262,144 for Gemma 4 31B IT. Maximum output per response: Gemma 4 31B IT up to 32,768, DeepSeek V4 Flash up to 384,000, Qwen3.5 Flash up to 65,536 tokens.
Which can read images, PDFs, audio or video?
Gemma 4 31B IT accepts text and images; DeepSeek V4 Flash accepts text; Qwen3.5 Flash accepts text, images and video. Qwen3.5 Flash handles the widest range of inputs.
Are any of these open source?
Gemma 4 31B IT and DeepSeek V4 Flash publishes its weights and can be self-hosted; Qwen3.5 Flash is proprietary.
Which is newer?
DeepSeek V4 Flash is the newest, released Apr 24, 2026. Gemma 4 31B IT came out Apr 2, 2026; Qwen3.5 Flash came out Feb 23, 2026. Knowledge cutoff: DeepSeek V4 Flash May 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.
