DeepSeek V4 Pro vs GLM-5.1 vs Kimi K2.5
Kimi K2.5 comes out ahead, 70 to 67 and 66 on our weighted score, and it is the cheaper option too.
Price in rating: Excluded · Include price
DeepSeek
DeepSeek V4 Pro
67/100- ECI150.2
- Price$1.60 / $3.33
- Context1M
Z.ai (Zhipu)
GLM-5.1
66/100- ECI150.7
- Price$1.40 / $4.40
- Context200K
- Our pick
Moonshot AI
Kimi K2.5
70/100- ECI148.8
- Price$0.60 / $3.00
- Context262K
Kimi K2.5 is our pick
Kimi K2.5 is the better all-round choice, scoring 70/100 against DeepSeek V4 Pro (67) and GLM-5.1 (66). It leads on inputs & features. DeepSeek V4 Pro wins on context window. The score weighs capability 67%, inputs & features 20%, context window 13%.
- CapabilityGLM-5.1Capabilities Index (ECI): GLM-5.1 150.7 · DeepSeek V4 Pro 150.2 · Kimi K2.5 148.8
- Lowest priceKimi K2.5Kimi K2.5 $1.20 · DeepSeek V4 Pro $2.03 · GLM-5.1 $2.15 per 1M tokens (3:1 blend)
- Longest contextDeepSeek V4 ProDeepSeek V4 Pro 1,000,000 · Kimi K2.5 262,144 · GLM-5.1 200,000 tokens
- Widest inputsKimi K2.5DeepSeek V4 Pro: Text · GLM-5.1: Text · Kimi K2.5: Text, Images, Video
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | DeepSeek V4 Pro | GLM-5.1 | Kimi K2.5 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 67% | 77 | 78 | 76 |
| Inputs & features | 20% | 35 | 45 | 70 |
| Context window | 13% | 64 | 39 | 43 |
| Overall | 100% | 67/100 | 66/100 | 70/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 150.2 | 150.7 (best) | 148.8 |
| ECI rank | #67 of 158 | #66 of 158 (best) | #73 of 158 |
| GPQA DiamondGraduate-level science questions | 90.9% (best) | 89.9% | 87.6% |
| FrontierMath Tiers 1–3Research-level mathematics | 45.3% (best) | 36.8% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 96.7% (best) | 93.3% | 92.2% |
| SWE-bench VerifiedFixing real GitHub issues | 77.6% (best) | 74.2% | 73.8% |
| SimpleQA VerifiedShort factual questions | 47.0% (best) | 34.0% | 34.3% |
| Price per million tokens | |||
| Input | $1.60 | $1.40 | $0.60 (best) |
| Output | $3.33 | $4.40 | $3.00 (best) |
| Cached input | — | $0.26 | — |
| Blended (3:1) | $2.03 | $2.15 | $1.20 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 65 providers | Official Z.AI API | Median of 36 providers |
| Limits | |||
| Context window | 1,000,000 tokens (best) | 200,000 tokens | 262,144 tokens |
| Max output | 384,000 tokens (best) | 131,072 tokens | 262,144 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | 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 | No | Yes | No |
| Availability | |||
| Weights | Open | Open | Open |
| API model ID | — | glm-5.1 | — |
| API providers | 67 (best) | 46 | 36 |
| Released | Apr 24, 2026 | Apr 7, 2026 | Jan 27, 2026 |
| Knowledge cutoff | May 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.
DeepSeek V4 Pro$22.66
GLM-5.1$22.80
Kimi K2.5$12.00
Which should you choose?
Which is better: DeepSeek V4 Pro, GLM-5.1 or Kimi K2.5?
Kimi K2.5 is the better all-round choice, scoring 70/100 against DeepSeek V4 Pro (67) and GLM-5.1 (66). It leads on inputs & features. DeepSeek V4 Pro wins on context window. The score weighs capability 67%, inputs & features 20%, context window 13%.
Which is cheaper, DeepSeek V4 Pro, GLM-5.1 or Kimi K2.5?
Kimi K2.5 is cheaper at $0.60 input / $3.00 output per million tokens (median across 36 API providers). DeepSeek V4 Pro costs $1.60 input / $3.33 output per million tokens (median across 65 API providers); GLM-5.1 costs $1.40 input / $4.40 output per million tokens (official Z.AI API price). At a typical mix of three input tokens to one output token, that is $1.20 per million tokens for Kimi K2.5 versus $2.03 for DeepSeek V4 Pro (1.7× as much) and $2.15 for GLM-5.1 (1.8× as much).
Which scores higher on benchmarks?
GLM-5.1 scores higher on the Capabilities Index (ECI): GLM-5.1 150.7 (#66 of 158), DeepSeek V4 Pro 150.2 (#67 of 158) and Kimi K2.5 148.8 (#73 of 158). The confidence ranges of the top two overlap (148.8–152.8 vs 148.5–152.0), so treat the gap as small. On individual benchmarks: GPQA Diamond — DeepSeek V4 Pro 90.9%, GLM-5.1 89.9%, Kimi K2.5 87.6%; OTIS Mock AIME 2024–2025 — DeepSeek V4 Pro 96.7%, GLM-5.1 93.3%, Kimi K2.5 92.2%; SWE-bench Verified — DeepSeek V4 Pro 77.6%, GLM-5.1 74.2%, Kimi K2.5 73.8%; SimpleQA Verified — DeepSeek V4 Pro 47.0%, Kimi K2.5 34.3%, GLM-5.1 34.0%.
Which is better for coding?
DeepSeek V4 Pro resolves more real GitHub issues on SWE-bench Verified: DeepSeek V4 Pro 77.6%, GLM-5.1 74.2% and Kimi K2.5 73.8%. All three support tool calling for agent workflows.
Which has the bigger context window?
DeepSeek V4 Pro has the largest context window at 1,000,000 tokens, against 262,144 for Kimi K2.5 and 200,000 for GLM-5.1. Maximum output per response: DeepSeek V4 Pro up to 384,000, GLM-5.1 up to 131,072, Kimi K2.5 up to 262,144 tokens.
Which can read images, PDFs, audio or video?
DeepSeek V4 Pro accepts text; GLM-5.1 accepts text; Kimi K2.5 accepts text, images and video. Kimi K2.5 handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights, so you can self-host them.
Which is newer?
DeepSeek V4 Pro is the newest, released Apr 24, 2026. GLM-5.1 came out Apr 7, 2026; Kimi K2.5 came out Jan 27, 2026. Knowledge cutoff: DeepSeek V4 Pro May 2025, Kimi K2.5 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.