Kimi K3 vs Claude Opus 4.8 vs GPT-5.4
Too close to call on our weighted score (Kimi K3 65, GPT-5.4 65, Claude Opus 4.8 63). The right pick depends on what you value most.
Moonshot AIKimi K3
65/100- ECI157.6
- Price$3.00 / $15.00
- Context1.05M
AnthropicClaude Opus 4.8
63/100- ECI158.3
- Price$5.00 / $25.00
- Context1M
OpenAIGPT-5.4
65/100- ECI156.9
- Price$2.50 / $15.00
- Context1.05M
Too close to call
It is close. Our weighted score puts them within a point (Kimi K3 65/100, GPT-5.4 65/100, Claude Opus 4.8 63/100), so choose by what matters most for your work: Claude Opus 4.8 for raw capability and GPT-5.4 on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityClaude Opus 4.8Capabilities Index (ECI): Claude Opus 4.8 158.3 · Kimi K3 157.6 · GPT-5.4 156.9
- Lowest priceGPT-5.4GPT-5.4 $5.63 · Kimi K3 $6.00 · Claude Opus 4.8 $10.00 per 1M tokens (3:1 blend)
- Longest contextGPT-5.4 and Kimi K3GPT-5.4 1,050,000 · Kimi K3 1,048,576 · Claude Opus 4.8 1,000,000 tokens
- Widest inputsSame inputsKimi K3: Text, Images, Video · Claude Opus 4.8: Text, Images, PDFs · GPT-5.4: Text, Images, PDFs
- Self-hostingKimi K3Publishes downloadable weights
| Measure | Weight | Kimi K3 | Claude Opus 4.8 | GPT-5.4 |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 88 | 89 | 87 |
| Price | 25% | 13 | 2 | 14 |
| Inputs & features | 15% | 80 | 80 | 80 |
| Context window | 10% | 61 | 60 | 61 |
| Overall | 100% | 65/100 | 63/100 | 65/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Kimi K3Moonshot AI | Claude Opus 4.8Anthropic | GPT-5.4OpenAI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 157.6 | 158.3 (best) | 156.9 |
| ECI rank | #13 of 148 | #12 of 148 (best) | #16 of 148 |
| GPQA DiamondGraduate-level science questions | 93.1% | 91.0% | 93.3% (best) |
| FrontierMath Tiers 1–3Research-level mathematics | 72.2% | 80.0% (best) | 78.6% |
| OTIS Mock AIME 2024–2025Competition mathematics | 97.2% | 98.3% (best) | 97.8% |
| SWE-bench VerifiedFixing real GitHub issues | — | — | 76.9% |
| SimpleQA VerifiedShort factual questions | 50.6% | 53.0% (best) | 45.1% |
| Price per million tokens | |||
| Input | $3.00 | $5.00 | $2.50 (best) |
| Output | $15.00 (best) | $25.00 | $15.00 (best) |
| Cached input | $0.30 | $0.50 | $0.25 (best) |
| Blended (3:1) | $6.00 | $10.00 | $5.63 (best) |
| Long-context rate | Same rate | Same rate | Over 272K: $5.00 / $22.50 |
| Price source | Official Moonshot AI API | Official Anthropic API | Official OpenAI API |
| Limits | |||
| Context window | 1,048,576 tokens | 1,000,000 tokens | 1,050,000 tokens (best) |
| Max output | 131,072 tokens (best) | 128,000 tokens | 128,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | No | Yes | Yes |
| Audio | No | No | No |
| Video | Yes | No | No |
| Reasoning | Yeslow · high · max | Yeslow · medium · high · xhigh · max | Yeslow · medium · high · xhigh |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | Yes |
| Availability | |||
| Weights | Open | Proprietary | Proprietary |
| API model ID | kimi-k3 | claude-opus-4-8 | gpt-5.4 |
| API providers | 68 (best) | 45 | 36 |
| Released | Jul 16, 2026 | May 28, 2026 | Mar 5, 2026 |
| Knowledge cutoff | — | Jan 2026 | Aug 31, 2025 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Kimi K3$60.00
- Claude Opus 4.8$100.00
- GPT-5.4$55.00
Which should you choose?
Which is better: Kimi K3, Claude Opus 4.8 or GPT-5.4?
It is close. Our weighted score puts them within a point (Kimi K3 65/100, GPT-5.4 65/100, Claude Opus 4.8 63/100), so choose by what matters most for your work: Claude Opus 4.8 for raw capability and GPT-5.4 on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, Kimi K3, Claude Opus 4.8 or GPT-5.4?
GPT-5.4 is cheaper at $2.50 input / $15.00 output per million tokens (official OpenAI API price). Kimi K3 costs $3.00 input / $15.00 output per million tokens (official Moonshot AI API price); Claude Opus 4.8 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 $5.63 per million tokens for GPT-5.4 versus $6.00 for Kimi K3 (1.1× as much) and $10.00 for Claude Opus 4.8 (1.8× as much).
Which scores higher on benchmarks?
Claude Opus 4.8 scores higher on the Capabilities Index (ECI): Claude Opus 4.8 158.3 (#12 of 148), Kimi K3 157.6 (#13 of 148) and GPT-5.4 156.9 (#16 of 148). The confidence ranges of the top two overlap (156.1–160.7 vs 154.9–160.4), so treat the gap as small. On individual benchmarks: GPQA Diamond — GPT-5.4 93.3%, Kimi K3 93.1%, Claude Opus 4.8 91.0%; FrontierMath Tiers 1–3 — Claude Opus 4.8 80.0%, GPT-5.4 78.6%, Kimi K3 72.2%; OTIS Mock AIME 2024–2025 — Claude Opus 4.8 98.3%, GPT-5.4 97.8%, Kimi K3 97.2%; SimpleQA Verified — Claude Opus 4.8 53.0%, Kimi K3 50.6%, GPT-5.4 45.1%.
Which is better for coding?
There are no published SWE-bench Verified results for Kimi K3 and Claude Opus 4.8 yet, so there is no like-for-like coding score. On overall capability, Claude Opus 4.8 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-5.4 and Kimi K3 have the largest context windows (1,050,000 and 1,048,576 tokens), against 1,000,000 for Claude Opus 4.8. Maximum output per response: Kimi K3 up to 131,072, Claude Opus 4.8 up to 128,000, GPT-5.4 up to 128,000 tokens.
Which can read images, PDFs, audio or video?
Kimi K3 accepts text, images and video; Claude Opus 4.8 accepts text, images and PDFs; GPT-5.4 accepts text, images and PDFs. They handle the same number of input types.
Are any of these open source?
Kimi K3 publishes its weights and can be self-hosted; Claude Opus 4.8 and GPT-5.4 is proprietary.
Which is newer?
Kimi K3 is the newest, released Jul 16, 2026. Claude Opus 4.8 came out May 28, 2026; GPT-5.4 came out Mar 5, 2026. Knowledge cutoff: Claude Opus 4.8 Jan 2026, GPT-5.4 Aug 31, 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.
