GPT-5.1 vs Kimi K2.7 Code vs Claude Opus 4.5
Kimi K2.7 Code comes out ahead, 64 to 60 and 55 on our weighted score, and it is the cheaper option too.
OpenAIGPT-5.1
60/100- ECI149.7
- Price$1.25 / $10.00
- Context400K
- Our pick
Moonshot AIKimi K2.7 Code
64/100- ECI150.0
- Price$0.95 / $4.00
- Context262K
AnthropicClaude Opus 4.5
55/100- ECI150.1
- Price$5.00 / $25.00
- Context200K
Kimi K2.7 Code is our pick
Kimi K2.7 Code is the better all-round choice, scoring 64/100 against GPT-5.1 (60) and Claude Opus 4.5 (55). It leads on price. GPT-5.1 wins on context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityClaude Opus 4.5Capabilities Index (ECI): Claude Opus 4.5 150.1 · Kimi K2.7 Code 150.0 · GPT-5.1 149.7
- Lowest priceKimi K2.7 CodeKimi K2.7 Code $1.71 · GPT-5.1 $3.44 · Claude Opus 4.5 $10.00 per 1M tokens (3:1 blend)
- Longest contextGPT-5.1GPT-5.1 400,000 · Kimi K2.7 Code 262,144 · Claude Opus 4.5 200,000 tokens
- Widest inputsKimi K2.7 Code and Claude Opus 4.5GPT-5.1: Text, Images · Kimi K2.7 Code: Text, Images, Video · Claude Opus 4.5: Text, Images, PDFs
- Self-hostingKimi K2.7 CodePublishes downloadable weights
| Measure | Weight | GPT-5.1 | Kimi K2.7 Code | Claude Opus 4.5 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 78 | 78 | 78 |
| Price | 25% | 24 | 39 | 2 |
| Inputs & features | 15% | 70 | 80 | 80 |
| Context window | 10% | 44 | 37 | 32 |
| Overall | 100% | 60/100 | 64/100 | 55/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | GPT-5.1OpenAI | Kimi K2.7 CodeMoonshot AI | Claude Opus 4.5Anthropic |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 149.7 | 150.0 | 150.1 (best) |
| ECI rank | #52 of 148 | #49 of 148 | #48 of 148 (best) |
| GPQA DiamondGraduate-level science questions | 87.6% | 87.9% (best) | 86.1% |
| FrontierMath Tiers 1–3Research-level mathematics | — | 54.0% (best) | 34.4% |
| OTIS Mock AIME 2024–2025Competition mathematics | 88.6% | 95.6% (best) | 86.1% |
| SWE-bench VerifiedFixing real GitHub issues | 68.0% | — | 76.7% (best) |
| SimpleQA VerifiedShort factual questions | 48.0% (best) | 36.5% | 45.7% |
| Price per million tokens | |||
| Input | $1.25 | $0.95 (best) | $5.00 |
| Output | $10.00 | $4.00 (best) | $25.00 |
| Cached input | $0.125 (best) | $0.19 | $0.50 |
| Blended (3:1) | $3.44 | $1.71 (best) | $10.00 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official OpenAI API | Official Moonshot AI API | Official Anthropic API |
| Limits | |||
| Context window | 400,000 tokens (best) | 262,144 tokens | 200,000 tokens |
| Max output | 128,000 tokens | 262,144 tokens (best) | 64,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | No | No | Yes |
| Audio | No | No | No |
| Video | No | Yes | No |
| Reasoning | Yeslow · medium · high | Yes | Yeslow · medium · high |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | Yes |
| Availability | |||
| Weights | Proprietary | Open | Proprietary |
| API model ID | gpt-5.1 | kimi-k2.7-code | claude-opus-4-5 |
| API providers | 21 | 51 (best) | 28 |
| Released | Nov 13, 2025 | Jun 12, 2026 | Nov 24, 2025 |
| Knowledge cutoff | Sep 30, 2024 | Jan 2025 | May 2025 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- GPT-5.1$32.50
- Kimi K2.7 Code$17.50
- Claude Opus 4.5$100.00
Which should you choose?
Which is better: GPT-5.1, Kimi K2.7 Code or Claude Opus 4.5?
Kimi K2.7 Code is the better all-round choice, scoring 64/100 against GPT-5.1 (60) and Claude Opus 4.5 (55). It leads on price. GPT-5.1 wins on context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, GPT-5.1, Kimi K2.7 Code or Claude Opus 4.5?
Kimi K2.7 Code is cheaper at $0.95 input / $4.00 output per million tokens (official Moonshot AI API price). GPT-5.1 costs $1.25 input / $10.00 output per million tokens (official OpenAI API price); Claude Opus 4.5 costs $5.00 input / $25.00 output per million tokens (official Anthropic 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 $3.44 for GPT-5.1 (2× as much) and $10.00 for Claude Opus 4.5 (5.8× as much).
Which scores higher on benchmarks?
Claude Opus 4.5 scores higher on the Capabilities Index (ECI): Claude Opus 4.5 150.1 (#48 of 148), Kimi K2.7 Code 150.0 (#49 of 148) and GPT-5.1 149.7 (#52 of 148). The confidence ranges of the top two overlap (147.9–153.0 vs 148.1–151.8), so treat the gap as small. On individual benchmarks: GPQA Diamond — Kimi K2.7 Code 87.9%, GPT-5.1 87.6%, Claude Opus 4.5 86.1%; OTIS Mock AIME 2024–2025 — Kimi K2.7 Code 95.6%, GPT-5.1 88.6%, Claude Opus 4.5 86.1%; SimpleQA Verified — GPT-5.1 48.0%, Claude Opus 4.5 45.7%, Kimi K2.7 Code 36.5%.
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, Claude Opus 4.5 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-5.1 has the largest context window at 400,000 tokens, against 262,144 for Kimi K2.7 Code and 200,000 for Claude Opus 4.5. Maximum output per response: GPT-5.1 up to 128,000, Kimi K2.7 Code up to 262,144, Claude Opus 4.5 up to 64,000 tokens.
Which can read images, PDFs, audio or video?
GPT-5.1 accepts text and images; Kimi K2.7 Code accepts text, images and video; Claude Opus 4.5 accepts text, images and PDFs. Kimi K2.7 Code handles the widest range of inputs.
Are any of these open source?
Kimi K2.7 Code publishes its weights and can be self-hosted; GPT-5.1 and Claude Opus 4.5 is proprietary.
Which is newer?
Kimi K2.7 Code is the newest, released Jun 12, 2026. Claude Opus 4.5 came out Nov 24, 2025; GPT-5.1 came out Nov 13, 2025. Knowledge cutoff: GPT-5.1 Sep 30, 2024, Kimi K2.7 Code Jan 2025, Claude Opus 4.5 May 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.
