Compare AI models
| Benchmark | Opus 5.5 | GPT-6.1 Sol | Kimi K3 |
|---|---|---|---|
| Humanity's Last Exam | 54.7 | 49.9 | 46.9 |
| Terminal-Bench 4.0 | 52.5 | 48 | 12.6 |
| AutomationBench-AA | 61.2 | 62.6 | 58.3 |
| Arena Text · creative writing | 1,519 · high | 1,458 · max | 1,461 |
| MMMU-Pro (vision) | 85.7 | 83.9 | 80.5 |
Specs
| Spec | Opus 5.5 | GPT-6.1 Sol | Kimi K3 |
|---|---|---|---|
| Input, per 1M | $4 | $2 | $3 |
| Output, per 1M | $20 | $10 | $15 |
| Cost per task? | $1.34 | $0.21 | $2.00 |
| Speed, tok/s | 81 | 45 | 112 |
| Context | 1M | 1.05M | 1M |
| Weights | Closed | Closed | Open |
| Released | Sep 2026 | Sep 2026 | Jul 2026 |
| Memory (4-bit) | — | — | 1,668 GB |
| Licence | — | — | kimi-k3 |
| Commercial use | — | — | Restricted |
| See images | ✓ | ✓ | ✓ |
| Read PDFs | ✓ | Partial | Partial |
| Hear audio | — | — | — |
| Watch video | — | — | ✓ |
| Call tools | ✓ | ✓ | ✓ |
| Force a tool call | — | Partial | ✓ |
| Return strict JSON | ✓ | ✓ | ✓ |
| Search the web | ✓ | ✓ | Partial |
| Run code | ✓ | ✓ | ? |
| Use a computer | ✓ | ✓ | ? |
What breaks when you switch
Remove unsupported parameters›
With reasoning enabled, remove temperature, top_p and top_logprobs, plus Chat Completions logprobs or Responses message.output_text.logprobs includes.
Responses API for tool calling · Chat Completions›
Use Responses for tools; Chat Completions supports this model without tool calling.
No none or minimal reasoning›
The none and minimal reasoning efforts are unsupported; choose low, medium, high, xhigh or max.
More than 272K input tokens›
Prompts above 272K input tokens charge 2× input and cache rates and 1.5× output rates for the entire request.
Cache writes billed at 1.25x›
Cache writes cost 1.25× the uncached input token rate.
Ultrafast prices 6x Standard›
Ultrafast mode costs 6× Standard token prices.
Sampling parameters are fixed›
temperature, top_p, n and penalty values are fixed; omit them from requests.
No public image URLs›
Vision input rejects public image URLs; use base64 or ms:// file references in a content array.
Web search is being updated›
Web search is not recommended for near-term production workflows; avoid depending on it in production.
Thinking mode is always enabled›
K3 always has thinking enabled; control effort with the top-level reasoning_effort field using low, high or max.
Context: 1.05M → 1M
No forced tool use›
Forced tool_choice any or tool returns HTTP 400; remove the forced choice.
Thinking is always on›
Disabled thinking or a manual budget returns HTTP 400; omit thinking or use adaptive thinking.
Remove sampling parameters›
Non-default temperature, top_p or top_k returns HTTP 400; omit these parameters and use prompting.
No assistant prefill›
Assistant prefill returns HTTP 400; use structured outputs or system instructions, with system instructions on Bedrock.
Old computer tool rejected · Claude API / Google Cloud›
The computer_20251124 tool returns HTTP 400 on the Claude API and Google Cloud; use computer_toolset_20260801 there.
Return thinking blocks unmodified›
Edited, reordered or partially dropped thinking blocks return HTTP 400; echo assistant messages complete and unmodified with tool results.
Context: 1.05M → 1M
Sampling parameters are fixed›
temperature, top_p, n and penalty values are fixed; omit them from requests.
No public image URLs›
Vision input rejects public image URLs; use base64 or ms:// file references in a content array.
Web search is being updated›
Web search is not recommended for near-term production workflows; avoid depending on it in production.
Thinking mode is always enabled›
K3 always has thinking enabled; control effort with the top-level reasoning_effort field using low, high or max.
No forced tool use›
Forced tool_choice any or tool returns HTTP 400; remove the forced choice.
Thinking is always on›
Disabled thinking or a manual budget returns HTTP 400; omit thinking or use adaptive thinking.
Remove sampling parameters›
Non-default temperature, top_p or top_k returns HTTP 400; omit these parameters and use prompting.
No assistant prefill›
Assistant prefill returns HTTP 400; use structured outputs or system instructions, with system instructions on Bedrock.
Old computer tool rejected · Claude API / Google Cloud›
The computer_20251124 tool returns HTTP 400 on the Claude API and Google Cloud; use computer_toolset_20260801 there.
Return thinking blocks unmodified›
Edited, reordered or partially dropped thinking blocks return HTTP 400; echo assistant messages complete and unmodified with tool results.
Remove unsupported parameters›
With reasoning enabled, remove temperature, top_p and top_logprobs, plus Chat Completions logprobs or Responses message.output_text.logprobs includes.
Responses API for tool calling · Chat Completions›
Use Responses for tools; Chat Completions supports this model without tool calling.
No none or minimal reasoning›
The none and minimal reasoning efforts are unsupported; choose low, medium, high, xhigh or max.
More than 272K input tokens›
Prompts above 272K input tokens charge 2× input and cache rates and 1.5× output rates for the entire request.
Cache writes billed at 1.25x›
Cache writes cost 1.25× the uncached input token rate.
Ultrafast prices 6x Standard›
Ultrafast mode costs 6× Standard token prices.