Qwen3.7 Max vs GLM-5 vs Gemini 3.5 Flash
Gemini 3.5 Flash comes out ahead, 69 to 58 and 55 on our weighted score, though GLM-5 is 2.2× cheaper per token.
Alibaba (Qwen)Qwen3.7 Max
58/100- ECI153.7
- Price$2.50 / $7.50
- Context1M
Z.ai (Zhipu)GLM-5
55/100- ECI145.8
- Price$1.00 / $3.20
- Context205K
- 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 Qwen3.7 Max (58) and GLM-5 (55). It leads on inputs & features. GLM-5 wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityGemini 3.5 FlashCapabilities Index (ECI): Gemini 3.5 Flash 154.5 · Qwen3.7 Max 153.7 · GLM-5 145.8
- Lowest priceGLM-5GLM-5 $1.55 · Gemini 3.5 Flash $3.38 · Qwen3.7 Max $3.75 per 1M tokens (3:1 blend)
- Longest contextGemini 3.5 FlashGemini 3.5 Flash 1,048,576 · Qwen3.7 Max 1,000,000 · GLM-5 204,800 tokens
- Widest inputsGemini 3.5 FlashQwen3.7 Max: Text · GLM-5: Text · Gemini 3.5 Flash: Text, Images, PDFs, Audio, Video
- Self-hostingGLM-5Publishes downloadable weights
| Measure | Weight | Qwen3.7 Max | GLM-5 | Gemini 3.5 Flash |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 83 | 73 | 84 |
| Price | 25% | 23 | 41 | 25 |
| Inputs & features | 15% | 35 | 35 | 100 |
| Context window | 10% | 60 | 32 | 61 |
| Overall | 100% | 58/100 | 55/100 | 69/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Qwen3.7 MaxAlibaba (Qwen) | GLM-5Z.ai (Zhipu) | Gemini 3.5 FlashGoogle |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 153.7 | 145.8 | 154.5 (best) |
| ECI rank | #37 of 148 | #74 of 148 | #33 of 148 (best) |
| GPQA DiamondGraduate-level science questions | 90.9% | 87.8% | 92.8% (best) |
| FrontierMath Tiers 1–3Research-level mathematics | 64.6% (best) | — | 62.8% |
| OTIS Mock AIME 2024–2025Competition mathematics | 95.6% (best) | 80.0% | 95.6% (best) |
| SWE-bench VerifiedFixing real GitHub issues | 77.3% | 72.1% | 79.3% (best) |
| SimpleQA VerifiedShort factual questions | 55.8% | — | 66.2% (best) |
| Price per million tokens | |||
| Input | $2.50 | $1.00 (best) | $1.50 |
| Output | $7.50 | $3.20 (best) | $9.00 |
| Cached input | $0.50 | $0.20 | $0.15 (best) |
| Blended (3:1) | $3.75 | $1.55 (best) | $3.38 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Alibaba API | Official Z.AI API | Official Google API |
| Limits | |||
| Context window | 1,000,000 tokens | 204,800 tokens | 1,048,576 tokens (best) |
| Max output | 65,536 tokens | 131,072 tokens (best) | 65,536 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | Yes |
| PDFs | No | No | Yes |
| Audio | No | No | Yes |
| Video | No | No | Yes |
| Reasoning | Yes | Yes | Yesminimal · low · medium · high |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | Yes |
| Availability | |||
| Weights | Proprietary | Open | Proprietary |
| API model ID | qwen3.7-max | glm-5 | gemini-3.5-flash |
| API providers | 26 | 27 | 32 (best) |
| Released | May 21, 2026 | Feb 12, 2026 | May 19, 2026 |
| 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.
- Qwen3.7 Max$40.00
- GLM-5$16.40
- Gemini 3.5 Flash$33.00
Which should you choose?
Which is better: Qwen3.7 Max, GLM-5 or Gemini 3.5 Flash?
Gemini 3.5 Flash is the better all-round choice, scoring 69/100 against Qwen3.7 Max (58) and GLM-5 (55). It leads on inputs & features. GLM-5 wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, Qwen3.7 Max, GLM-5 or Gemini 3.5 Flash?
GLM-5 is cheaper at $1.00 input / $3.20 output per million tokens (official Z.AI API price). Gemini 3.5 Flash costs $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). At a typical mix of three input tokens to one output token, that is $1.55 per million tokens for GLM-5 versus $3.38 for Gemini 3.5 Flash (2.2× as much) and $3.75 for Qwen3.7 Max (2.4× as much).
Which scores higher on benchmarks?
Gemini 3.5 Flash scores higher on the Capabilities Index (ECI): Gemini 3.5 Flash 154.5 (#33 of 148), Qwen3.7 Max 153.7 (#37 of 148) and GLM-5 145.8 (#74 of 148). The confidence ranges of the top two overlap (152.5–156.6 vs 151.9–156.0), so treat the gap as small. On individual benchmarks: GPQA Diamond — Gemini 3.5 Flash 92.8%, Qwen3.7 Max 90.9%, GLM-5 87.8%; OTIS Mock AIME 2024–2025 — Qwen3.7 Max 95.6%, Gemini 3.5 Flash 95.6%, GLM-5 80.0%; SWE-bench Verified — Gemini 3.5 Flash 79.3%, Qwen3.7 Max 77.3%, GLM-5 72.1%.
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 GLM-5 72.1%. 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 204,800 for GLM-5. Maximum output per response: Qwen3.7 Max up to 65,536, GLM-5 up to 131,072, Gemini 3.5 Flash up to 65,536 tokens.
Which can read images, PDFs, audio or video?
Qwen3.7 Max accepts text; GLM-5 accepts text; 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?
GLM-5 publishes its weights and can be self-hosted; Qwen3.7 Max and Gemini 3.5 Flash is proprietary.
Which is newer?
Qwen3.7 Max is the newest, released May 21, 2026. Gemini 3.5 Flash came out May 19, 2026; GLM-5 came out Feb 12, 2026. Knowledge cutoff: 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.
