Gemini 2.5 Flash Preview 05-20 vs Qwen3 235B-A22B Instruct 2507 vs DeepSeek R1 0528
Gemini 2.5 Flash Preview 05-20 comes out ahead, 67 to 57 and 53 on our weighted score, though Qwen3 235B-A22B Instruct 2507 is 2× cheaper per token.
- Our pick
GoogleGemini 2.5 Flash Preview 05-20
67/100- ECI141.5
- Price$0.146 / $1.96
- Context1.05M
Alibaba (Qwen)Qwen3 235B-A22B Instruct 2507
57/100- ECI138.8
- Price$0.199 / $0.60
- Context262K
DeepSeekDeepSeek R1 0528
53/100- ECI141.2
- Price$0.512 / $2.19
- Context164K
Gemini 2.5 Flash Preview 05-20 is our pick
Gemini 2.5 Flash Preview 05-20 is the better all-round choice, scoring 67/100 against Qwen3 235B-A22B Instruct 2507 (57) and DeepSeek R1 0528 (53). It leads on inputs & features and context window. Qwen3 235B-A22B Instruct 2507 wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityGemini 2.5 Flash Preview 05-20Capabilities Index (ECI): Gemini 2.5 Flash Preview 05-20 141.5 · DeepSeek R1 0528 141.2 · Qwen3 235B-A22B Instruct 2507 138.8
- Lowest priceQwen3 235B-A22B Instruct 2507Qwen3 235B-A22B Instruct 2507 $0.299 · Gemini 2.5 Flash Preview 05-20 $0.60 · DeepSeek R1 0528 $0.932 per 1M tokens (3:1 blend)
- Longest contextGemini 2.5 Flash Preview 05-20Gemini 2.5 Flash Preview 05-20 1,048,576 · Qwen3 235B-A22B Instruct 2507 262,144 · DeepSeek R1 0528 163,840 tokens
- Widest inputsGemini 2.5 Flash Preview 05-20Gemini 2.5 Flash Preview 05-20: Text, Images, PDFs, Audio, Video · Qwen3 235B-A22B Instruct 2507: Text · DeepSeek R1 0528: Text
- Self-hostingQwen3 235B-A22B Instruct 2507 and DeepSeek R1 0528Publishes downloadable weights (Apache 2.0 and MIT)
| Measure | Weight | Gemini 2.5 Flash Preview 05-20 | Qwen3 235B-A22B Instruct 2507 | DeepSeek R1 0528 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 66 | 63 | 66 |
| Price | 25% | 58 | 72 | 49 |
| Inputs & features | 15% | 90 | 25 | 35 |
| Context window | 10% | 61 | 37 | 28 |
| Overall | 100% | 67/100 | 57/100 | 53/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Gemini 2.5 Flash Preview 05-20Google | Qwen3 235B-A22B Instruct 2507Alibaba (Qwen) | DeepSeek R1 0528DeepSeek |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 141.5 (best) | 138.8 | 141.2 |
| ECI rank | #106 of 165 (best) | #118 of 165 | #108 of 165 |
| GPQA DiamondGraduate-level science questions | — | — | 76.3% |
| OTIS Mock AIME 2024–2025Competition mathematics | 70.8% (best) | — | 66.4% |
| Price per million tokens | |||
| Input | $0.146 (best) | $0.199 | $0.512 |
| Output | $1.96 | $0.60 (best) | $2.19 |
| Cached input | — | — | — |
| Blended (3:1) | $0.60 | $0.299 (best) | $0.932 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 2 providers | Median of 23 providers | Median of 16 providers |
| Limits | |||
| Context window | 1,048,576 tokens (best) | 262,144 tokens | 163,840 tokens |
| Max output | 65,536 tokens (best) | 16,384 tokens | 32,768 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | No |
| PDFs | Yes | No | No |
| Audio | Yes | No | No |
| Video | Yes | No | No |
| Reasoning | Yes | No | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Proprietary | OpenApache 2.0 | OpenMIT |
| API model ID | — | — | — |
| API providers | 2 | 25 (best) | 16 |
| Released | May 20, 2025 | Jul 21, 2025 | May 28, 2025 |
| Knowledge cutoff | Jan 2025 | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Gemini 2.5 Flash Preview 05-20$5.39
- Qwen3 235B-A22B Instruct 2507$3.19
- DeepSeek R1 0528$9.50
Which should you choose?
Which is better: Gemini 2.5 Flash Preview 05-20, Qwen3 235B-A22B Instruct 2507 or DeepSeek R1 0528?
Gemini 2.5 Flash Preview 05-20 is the better all-round choice, scoring 67/100 against Qwen3 235B-A22B Instruct 2507 (57) and DeepSeek R1 0528 (53). It leads on inputs & features and context window. Qwen3 235B-A22B Instruct 2507 wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, Gemini 2.5 Flash Preview 05-20, Qwen3 235B-A22B Instruct 2507 or DeepSeek R1 0528?
Qwen3 235B-A22B Instruct 2507 is cheaper at $0.199 input / $0.60 output per million tokens (median across 23 API providers). Gemini 2.5 Flash Preview 05-20 costs $0.146 input / $1.96 output per million tokens (median across 2 API providers); DeepSeek R1 0528 costs $0.512 input / $2.19 output per million tokens (median across 16 API providers). At a typical mix of three input tokens to one output token, that is $0.299 per million tokens for Qwen3 235B-A22B Instruct 2507 versus $0.60 for Gemini 2.5 Flash Preview 05-20 (2× as much) and $0.932 for DeepSeek R1 0528 (3.1× as much).
Which scores higher on benchmarks?
Gemini 2.5 Flash Preview 05-20 scores higher on the Capabilities Index (ECI): Gemini 2.5 Flash Preview 05-20 141.5 (#106 of 165), DeepSeek R1 0528 141.2 (#108 of 165) and Qwen3 235B-A22B Instruct 2507 138.8 (#118 of 165). The confidence ranges of the top two overlap (139.3–142.9 vs 139.0–142.9), so treat the gap as small.
Which is better for coding?
There are no published SWE-bench Verified results for Gemini 2.5 Flash Preview 05-20, Qwen3 235B-A22B Instruct 2507 and DeepSeek R1 0528 yet, so there is no like-for-like coding score. On overall capability, Gemini 2.5 Flash Preview 05-20 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 Preview 05-20 has the largest context window at 1,048,576 tokens, against 262,144 for Qwen3 235B-A22B Instruct 2507 and 163,840 for DeepSeek R1 0528. Maximum output per response: Gemini 2.5 Flash Preview 05-20 up to 65,536, Qwen3 235B-A22B Instruct 2507 up to 16,384, DeepSeek R1 0528 up to 32,768 tokens.
Which can read images, PDFs, audio or video?
Gemini 2.5 Flash Preview 05-20 accepts text, images, PDFs, audio and video; Qwen3 235B-A22B Instruct 2507 accepts text; DeepSeek R1 0528 accepts text. Gemini 2.5 Flash Preview 05-20 handles the widest range of inputs.
Are any of these open source?
Qwen3 235B-A22B Instruct 2507 and DeepSeek R1 0528 publishes its weights (Apache 2.0 and MIT) and can be self-hosted; Gemini 2.5 Flash Preview 05-20 is proprietary.
Which is newer?
Qwen3 235B-A22B Instruct 2507 is the newest, released Jul 21, 2025. DeepSeek R1 0528 came out May 28, 2025; Gemini 2.5 Flash Preview 05-20 came out May 20, 2025. Knowledge cutoff: Gemini 2.5 Flash Preview 05-20 Jan 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 Nov 2, 2026.
Related comparisons
- Gemini 2.5 Flash Preview 05-20 vs Kimi K2 InstructMoonshot AI · ECI 139.9
- Gemini 2.5 Flash Preview 05-20 vs QwQ 32BAlibaba (Qwen) · ECI 137.5
- Gemini 2.5 Flash Preview 05-20 vs GPT-5 MiniOpenAI · ECI 145.4
- Qwen3 235B-A22B Instruct 2507 vs GPT OSS 120BOpenAI · ECI 139.8
- Qwen3 235B-A22B Instruct 2507 vs DeepSeek-V3.1DeepSeek · ECI 139.8
- Qwen3 235B-A22B Instruct 2507 vs Kimi K2 InstructMoonshot AI · ECI 139.9
