Gemini 2.5 Pro vs GLM-5 vs Qwen3.6 27B
Gemini 2.5 Pro comes out ahead, 77 to 71 and 62 on our weighted score, though Qwen3.6 27B is 2.5× cheaper per token.
Price in rating: Excluded · Include price
- Our pick
Google
Gemini 2.5 Pro
77/100- ECI144.9
- Price$1.25 / $10.00
- Context1.05M
Z.ai (Zhipu)
GLM-5
62/100- ECI146.5
- Price$1.00 / $3.20
- Context205K
Alibaba (Qwen)
Qwen3.6 27B
71/100- ECI146.8
- Price$0.60 / $3.60
- Context262K
Gemini 2.5 Pro is our pick
Gemini 2.5 Pro is the better all-round choice, scoring 77/100 against Qwen3.6 27B (71) and GLM-5 (62). It leads on inputs & features and context window. The score weighs capability 67%, inputs & features 20%, context window 13%.
- CapabilityQwen3.6 27BCapabilities Index (ECI): Qwen3.6 27B 146.8 · GLM-5 146.5 · Gemini 2.5 Pro 144.9
- Lowest priceQwen3.6 27BQwen3.6 27B $1.35 · GLM-5 $1.55 · Gemini 2.5 Pro $3.44 per 1M tokens (3:1 blend)
- Longest contextGemini 2.5 ProGemini 2.5 Pro 1,048,576 · Qwen3.6 27B 262,144 · GLM-5 204,800 tokens
- Widest inputsGemini 2.5 ProGemini 2.5 Pro: Text, Images, PDFs, Audio, Video · GLM-5: Text · Qwen3.6 27B: Text, Images, Video
- Self-hostingGLM-5 and Qwen3.6 27BPublishes downloadable weights
| Measure | Weight | Gemini 2.5 Pro | GLM-5 | Qwen3.6 27B |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 67% | 73 | 74 | 74 |
| Inputs & features | 20% | 100 | 35 | 80 |
| Context window | 13% | 65 | 39 | 43 |
| Overall | 100% | 77/100 | 62/100 | 71/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 144.9 | 146.5 | 146.8 (best) |
| ECI rank | #92 of 158 | #85 of 158 | #84 of 158 (best) |
| GPQA DiamondGraduate-level science questions | 85.3% | 87.8% (best) | 85.9% |
| FrontierMath Tiers 1–3Research-level mathematics | 24.6% | — | 35.1% (best) |
| OTIS Mock AIME 2024–2025Competition mathematics | 84.7% | 80.0% | 91.1% (best) |
| SWE-bench VerifiedFixing real GitHub issues | 57.6% | 72.1% (best) | — |
| Price per million tokens | |||
| Input | $1.25 | $1.00 | $0.60 (best) |
| Output | $10.00 | $3.20 (best) | $3.60 |
| Cached input | $0.125 (best) | $0.20 | — |
| Blended (3:1) | $3.44 | $1.55 | $1.35 (best) |
| Long-context rate | Over 200K: $2.50 / $15.00 | Same rate | Same rate |
| Price source | Official Google API | Official Z.AI API | Official Alibaba API |
| Limits | |||
| Context window | 1,048,576 tokens (best) | 204,800 tokens | 262,144 tokens |
| Max output | 65,536 tokens | 131,072 tokens (best) | 65,536 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | Yes |
| PDFs | Yes | No | No |
| Audio | Yes | No | No |
| Video | Yes | No | Yes |
| Reasoning | Yes | Yes | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | Yes |
| Availability | |||
| Weights | Proprietary | Open | Open |
| API model ID | gemini-2.5-pro | glm-5 | qwen3.6-27b |
| API providers | 31 | 37 (best) | 29 |
| Released | Jun 17, 2025 | Feb 12, 2026 | Apr 22, 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.
Gemini 2.5 Pro$32.50
GLM-5$16.40
Qwen3.6 27B$13.20
Which should you choose?
Which is better: Gemini 2.5 Pro, GLM-5 or Qwen3.6 27B?
Gemini 2.5 Pro is the better all-round choice, scoring 77/100 against Qwen3.6 27B (71) and GLM-5 (62). It leads on inputs & features and context window. The score weighs capability 67%, inputs & features 20%, context window 13%.
Which is cheaper, Gemini 2.5 Pro, GLM-5 or Qwen3.6 27B?
Qwen3.6 27B is cheaper at $0.60 input / $3.60 output per million tokens (official Alibaba API price). GLM-5 costs $1.00 input / $3.20 output per million tokens (official Z.AI API price); Gemini 2.5 Pro costs $1.25 input / $10.00 output per million tokens (official Google API price). At a typical mix of three input tokens to one output token, that is $1.35 per million tokens for Qwen3.6 27B versus $1.55 for GLM-5 (1.1× as much) and $3.44 for Gemini 2.5 Pro (2.5× as much).
Which scores higher on benchmarks?
Qwen3.6 27B scores higher on the Capabilities Index (ECI): Qwen3.6 27B 146.8 (#84 of 158), GLM-5 146.5 (#85 of 158) and Gemini 2.5 Pro 144.9 (#92 of 158). The confidence ranges of the top two overlap (144.7–148.9 vs 145.0–148.1), so treat the gap as small. On individual benchmarks: GPQA Diamond — GLM-5 87.8%, Qwen3.6 27B 85.9%, Gemini 2.5 Pro 85.3%; OTIS Mock AIME 2024–2025 — Qwen3.6 27B 91.1%, Gemini 2.5 Pro 84.7%, GLM-5 80.0%.
Which is better for coding?
There are no published SWE-bench Verified results for Qwen3.6 27B yet, so there is no like-for-like coding score. On overall capability, Qwen3.6 27B 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 Pro has the largest context window at 1,048,576 tokens, against 262,144 for Qwen3.6 27B and 204,800 for GLM-5. Maximum output per response: Gemini 2.5 Pro up to 65,536, GLM-5 up to 131,072, Qwen3.6 27B up to 65,536 tokens.
Which can read images, PDFs, audio or video?
Gemini 2.5 Pro accepts text, images, PDFs, audio and video; GLM-5 accepts text; Qwen3.6 27B accepts text, images and video. Gemini 2.5 Pro handles the widest range of inputs.
Are any of these open source?
GLM-5 and Qwen3.6 27B publishes its weights and can be self-hosted; Gemini 2.5 Pro is proprietary.
Which is newer?
Qwen3.6 27B is the newest, released Apr 22, 2026. GLM-5 came out Feb 12, 2026; Gemini 2.5 Pro came out Jun 17, 2025. Knowledge cutoff: Gemini 2.5 Pro Jan 2025.
How do you decide the winner?
This rating uses capability (67%, independent benchmark results); inputs & features (20%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (13%, 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 18, 2026.