GLM-5.1 vs GPT-5.3 Codex vs Kimi K2.7 Code
Too close to call on our weighted score (Kimi K2.7 Code 64, GPT-5.3 Codex 64, GLM-5.1 57). The right pick depends on what you value most.
Z.ai (Zhipu)GLM-5.1
57/100- ECI149.9
- Price$1.40 / $4.40
- Context200K
OpenAIGPT-5.3 Codex
64/100- ECI156.8
- Price$1.75 / $14.00
- Context400K
Moonshot AIKimi K2.7 Code
64/100- ECI150.0
- Price$0.95 / $4.00
- Context262K
Too close to call
It is close. Our weighted score puts them within a point (Kimi K2.7 Code 64/100, GPT-5.3 Codex 64/100, GLM-5.1 57/100), so choose by what matters most for your work: GPT-5.3 Codex for raw capability and Kimi K2.7 Code on price. 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 · Kimi K2.7 Code 150.0 · GLM-5.1 149.9
- Lowest priceKimi K2.7 CodeKimi K2.7 Code $1.71 · GLM-5.1 $2.15 · GPT-5.3 Codex $4.81 per 1M tokens (3:1 blend)
- Longest contextGPT-5.3 CodexGPT-5.3 Codex 400,000 · Kimi K2.7 Code 262,144 · GLM-5.1 200,000 tokens
- Widest inputsGPT-5.3 Codex and Kimi K2.7 CodeGLM-5.1: Text · GPT-5.3 Codex: Text, Images, PDFs · Kimi K2.7 Code: Text, Images, Video
- Self-hostingGLM-5.1 and Kimi K2.7 CodePublishes downloadable weights
| Measure | Weight | GLM-5.1 | GPT-5.3 Codex | Kimi K2.7 Code |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 78 | 87 | 78 |
| Price | 25% | 34 | 18 | 39 |
| Inputs & features | 15% | 45 | 80 | 80 |
| Context window | 10% | 32 | 44 | 37 |
| Overall | 100% | 57/100 | 64/100 | 64/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | GLM-5.1Z.ai (Zhipu) | GPT-5.3 CodexOpenAI | Kimi K2.7 CodeMoonshot AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 149.9 | 156.8 (best) | 150.0 |
| ECI rank | #51 of 148 | #18 of 148 (best) | #49 of 148 |
| GPQA DiamondGraduate-level science questions | 89.9% (best) | — | 87.9% |
| FrontierMath Tiers 1–3Research-level mathematics | 36.8% | — | 54.0% (best) |
| OTIS Mock AIME 2024–2025Competition mathematics | 93.3% | — | 95.6% (best) |
| SWE-bench VerifiedFixing real GitHub issues | 74.2% | 74.8% (best) | — |
| SimpleQA VerifiedShort factual questions | 34.0% | — | 36.5% (best) |
| Price per million tokens | |||
| Input | $1.40 | $1.75 | $0.95 (best) |
| Output | $4.40 | $14.00 | $4.00 (best) |
| Cached input | $0.26 | $0.175 (best) | $0.19 |
| Blended (3:1) | $2.15 | $4.81 | $1.71 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Z.AI API | Official OpenAI API | Official Moonshot AI API |
| Limits | |||
| Context window | 200,000 tokens | 400,000 tokens (best) | 262,144 tokens |
| Max output | 131,072 tokens | 128,000 tokens | 262,144 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | Yes | No |
| Audio | No | No | No |
| Video | No | No | Yes |
| Reasoning | Yes | Yeslow · medium · high · xhigh | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | Yes |
| Availability | |||
| Weights | Open | Proprietary | Open |
| API model ID | glm-5.1 | gpt-5.3-codex | kimi-k2.7-code |
| API providers | 40 | 19 | 51 (best) |
| Released | Apr 7, 2026 | Feb 5, 2026 | Jun 12, 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.
- GLM-5.1$22.80
- GPT-5.3 Codex$45.50
- Kimi K2.7 Code$17.50
Which should you choose?
Which is better: GLM-5.1, GPT-5.3 Codex or Kimi K2.7 Code?
It is close. Our weighted score puts them within a point (Kimi K2.7 Code 64/100, GPT-5.3 Codex 64/100, GLM-5.1 57/100), so choose by what matters most for your work: GPT-5.3 Codex for raw capability and Kimi K2.7 Code on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, GLM-5.1, GPT-5.3 Codex or Kimi K2.7 Code?
Kimi K2.7 Code is cheaper at $0.95 input / $4.00 output per million tokens (official Moonshot AI API price). GLM-5.1 costs $1.40 input / $4.40 output per million tokens (official Z.AI 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 $1.71 per million tokens for Kimi K2.7 Code versus $2.15 for GLM-5.1 (1.3× as much) and $4.81 for GPT-5.3 Codex (2.8× 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), Kimi K2.7 Code 150.0 (#49 of 148) and GLM-5.1 149.9 (#51 of 148). Their confidence ranges do not overlap (153.5–160.8 vs 148.1–151.8), so the gap is a real one.
Which is better for coding?
There are no published SWE-bench Verified results for Kimi K2.7 Code yet, so there is no like-for-like coding score. On overall capability, GPT-5.3 Codex 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?
GPT-5.3 Codex has the largest context window at 400,000 tokens, against 262,144 for Kimi K2.7 Code and 200,000 for GLM-5.1. Maximum output per response: GLM-5.1 up to 131,072, GPT-5.3 Codex up to 128,000, Kimi K2.7 Code up to 262,144 tokens.
Which can read images, PDFs, audio or video?
GLM-5.1 accepts text; GPT-5.3 Codex accepts text, images and PDFs; Kimi K2.7 Code accepts text, images and video. GPT-5.3 Codex handles the widest range of inputs.
Are any of these open source?
GLM-5.1 and Kimi K2.7 Code publishes its weights and can be self-hosted; GPT-5.3 Codex is proprietary.
Which is newer?
Kimi K2.7 Code is the newest, released Jun 12, 2026. GLM-5.1 came out Apr 7, 2026; GPT-5.3 Codex came out Feb 5, 2026. Knowledge cutoff: GPT-5.3 Codex Aug 31, 2025, Kimi K2.7 Code 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.
