Qwen3.7 Max vs GPT-5.3 Codex vs Gemini 3.5 Flash
Gemini 3.5 Flash comes out ahead, 69 to 64 and 58 on our weighted score, and it is the cheaper option too.
Alibaba (Qwen)Qwen3.7 Max
58/100- ECI153.7
- Price$2.50 / $7.50
- Context1M
OpenAIGPT-5.3 Codex
64/100- ECI156.8
- Price$1.75 / $14.00
- Context400K
- Our pick
GoogleGemini 3.5 Flash
69/100- ECI154.5
- Price$1.50 / $9.00
- Context1.05M
Gemini 3.5 Flash is our pick
Gemini 3.5 Flash is the better all-round choice, scoring 69/100 against GPT-5.3 Codex (64) and Qwen3.7 Max (58). It leads on price and inputs & features. GPT-5.3 Codex wins on capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityGPT-5.3 CodexCapabilities Index (ECI): GPT-5.3 Codex 156.8 · Gemini 3.5 Flash 154.5 · Qwen3.7 Max 153.7
- Lowest priceGemini 3.5 FlashGemini 3.5 Flash $3.38 · Qwen3.7 Max $3.75 · GPT-5.3 Codex $4.81 per 1M tokens (3:1 blend)
- Longest contextGemini 3.5 FlashGemini 3.5 Flash 1,048,576 · Qwen3.7 Max 1,000,000 · GPT-5.3 Codex 400,000 tokens
- Widest inputsGemini 3.5 FlashQwen3.7 Max: Text · GPT-5.3 Codex: Text, Images, PDFs · Gemini 3.5 Flash: Text, Images, PDFs, Audio, Video
- Self-hostingNo open weightsAll three are available only through APIs
| Measure | Weight | Qwen3.7 Max | GPT-5.3 Codex | Gemini 3.5 Flash |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 83 | 87 | 84 |
| Price | 25% | 23 | 18 | 25 |
| Inputs & features | 15% | 35 | 80 | 100 |
| Context window | 10% | 60 | 44 | 61 |
| Overall | 100% | 58/100 | 64/100 | 69/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Qwen3.7 MaxAlibaba (Qwen) | GPT-5.3 CodexOpenAI | Gemini 3.5 FlashGoogle |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 153.7 | 156.8 (best) | 154.5 |
| ECI rank | #37 of 148 | #18 of 148 (best) | #33 of 148 |
| GPQA DiamondGraduate-level science questions | 90.9% | — | 92.8% (best) |
| FrontierMath Tiers 1–3Research-level mathematics | 64.6% (best) | — | 62.8% |
| OTIS Mock AIME 2024–2025Competition mathematics | 95.6% | — | 95.6% |
| SWE-bench VerifiedFixing real GitHub issues | 77.3% | 74.8% | 79.3% (best) |
| SimpleQA VerifiedShort factual questions | 55.8% | — | 66.2% (best) |
| Price per million tokens | |||
| Input | $2.50 | $1.75 | $1.50 (best) |
| Output | $7.50 (best) | $14.00 | $9.00 |
| Cached input | $0.50 | $0.175 | $0.15 (best) |
| Blended (3:1) | $3.75 | $4.81 | $3.38 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Alibaba API | Official OpenAI API | Official Google API |
| Limits | |||
| Context window | 1,000,000 tokens | 400,000 tokens | 1,048,576 tokens (best) |
| Max output | 65,536 tokens | 128,000 tokens (best) | 65,536 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | Yes | Yes |
| Audio | No | No | Yes |
| Video | No | No | Yes |
| Reasoning | Yes | Yeslow · medium · high · xhigh | Yesminimal · low · medium · high |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | Yes | Yes |
| Availability | |||
| Weights | Proprietary | Proprietary | Proprietary |
| API model ID | qwen3.7-max | gpt-5.3-codex | gemini-3.5-flash |
| API providers | 26 | 19 | 32 (best) |
| Released | May 21, 2026 | Feb 5, 2026 | May 19, 2026 |
| Knowledge cutoff | — | Aug 31, 2025 | 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.
- Qwen3.7 Max$40.00
- GPT-5.3 Codex$45.50
- Gemini 3.5 Flash$33.00
Which should you choose?
Which is better: Qwen3.7 Max, GPT-5.3 Codex or Gemini 3.5 Flash?
Gemini 3.5 Flash is the better all-round choice, scoring 69/100 against GPT-5.3 Codex (64) and Qwen3.7 Max (58). It leads on price and inputs & features. GPT-5.3 Codex wins on capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, Qwen3.7 Max, GPT-5.3 Codex or Gemini 3.5 Flash?
Gemini 3.5 Flash is cheaper at $1.50 input / $9.00 output per million tokens (official Google API price). Qwen3.7 Max costs $2.50 input / $7.50 output per million tokens (official Alibaba API price); GPT-5.3 Codex costs $1.75 input / $14.00 output per million tokens (official OpenAI API price). At a typical mix of three input tokens to one output token, that is $3.38 per million tokens for Gemini 3.5 Flash versus $3.75 for Qwen3.7 Max (1.1× as much) and $4.81 for GPT-5.3 Codex (1.4× as much).
Which scores higher on benchmarks?
GPT-5.3 Codex scores higher on the Capabilities Index (ECI): GPT-5.3 Codex 156.8 (#18 of 148), Gemini 3.5 Flash 154.5 (#33 of 148) and Qwen3.7 Max 153.7 (#37 of 148). The confidence ranges of the top two overlap (153.5–160.8 vs 152.5–156.6), so treat the gap as small. On individual benchmarks: SWE-bench Verified — Gemini 3.5 Flash 79.3%, Qwen3.7 Max 77.3%, GPT-5.3 Codex 74.8%.
Which is better for coding?
Gemini 3.5 Flash resolves more real GitHub issues on SWE-bench Verified: Gemini 3.5 Flash 79.3%, Qwen3.7 Max 77.3% and GPT-5.3 Codex 74.8%. All three support tool calling for agent workflows.
Which has the bigger context window?
Gemini 3.5 Flash has the largest context window at 1,048,576 tokens, against 1,000,000 for Qwen3.7 Max and 400,000 for GPT-5.3 Codex. Maximum output per response: Qwen3.7 Max up to 65,536, GPT-5.3 Codex up to 128,000, Gemini 3.5 Flash up to 65,536 tokens.
Which can read images, PDFs, audio or video?
Qwen3.7 Max accepts text; GPT-5.3 Codex accepts text, images and PDFs; Gemini 3.5 Flash accepts text, images, PDFs, audio and video. Gemini 3.5 Flash handles the widest range of inputs.
Are any of these open source?
No. Qwen3.7 Max, GPT-5.3 Codex and Gemini 3.5 Flash are proprietary and only available through APIs and apps.
Which is newer?
Qwen3.7 Max is the newest, released May 21, 2026. Gemini 3.5 Flash came out May 19, 2026; GPT-5.3 Codex came out Feb 5, 2026. Knowledge cutoff: GPT-5.3 Codex Aug 31, 2025, Gemini 3.5 Flash 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 Oct 4, 2026.
