Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | 397B | — |
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 256k | — |
| API pricingUSD per 1M tokens · lower wins | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | $0.60International (Singapore) | — |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | $3.60 | — |
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.36DeepInfra | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $2.34Alibaba | — |
| $195Alibaba | — | |
| Benchmarks | ||
Humanity's Last Exam · with toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | 48.3% | 44.4% |
BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | 78% | — |
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 76.4% | — |
SWE-Bench MultilingualMultilingual coding — Like SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | 69.3% | — |
LiveCodeBenchCompetitive coding — Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | 83.6% | — |
Terminal-Bench 2.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. | 52.5% | — |
IFEvalAgentic tasks — following verifiable instructions in generated responses | 92.6% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | 69% | — |
Humanity's Last Exam · no toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. | 28.7% | — |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 88.4% | — |
IFBenchInstruction following — Tests whether the AI can follow detailed instructions and satisfy multiple constraints at once. Higher is better. | 76.5% | — |
MMLU-ProKnowledge — accuracy on the ten-option MMLU-Pro benchmark | 87.8% | — |
OSWorld-VerifiedAgentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. | 62.2% | — |
CharXiv ReasoningChart reasoning — Can the AI read and reason about complex charts and figures, not just text? Higher is better. | 80.8% | — |
MMMU-ProMultimodal reasoning — A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | 79% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 85% | — |
| Overview | ||
| Company | Qwen | SpaceXSI |
| Release date | Feb 16 2026 | Jul 9 2025 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
Qwen3.5vsClaude Fable 5.2Grok 4 HeavyvsClaude Fable 5.2Qwen3.5vsGPT-6.2 AstraGrok 4 HeavyvsGPT-6.2 AstraQwen3.5vsGemini 4 NeonGrok 4 HeavyvsGemini 4 NeonQwen3.5vsMuse EmberGrok 4 HeavyvsMuse EmberQwen3.5vsDeepSeek-V4.1-Flash-1017Grok 4 HeavyvsDeepSeek-V4.1-Flash-1017Qwen3.5vsMistral Large 4Grok 4 HeavyvsMistral Large 4Frequently asked questions
Qwen3.5 leads Grok 4 Heavy on 1 of the 1 benchmark they both report (Humanity's Last Exam). Only Qwen3.5 has a verified first-party price for an available API: $0.60 per million input tokens and $3.60 per million output tokens. No currently available pay-as-you-go API rate is tracked for Grok 4 Heavy. The listed Qwen3.5 rates use the “International (Singapore)” pricing scope. Grok 4 Heavy shipped 222 days before Qwen3.5, so benchmark comparisons should account for the intervening progress.
Qwen3.5 is open weight, while Grok 4 Heavy is closed.
On Humanity's Last Exam · with tools, Qwen3.5 leads at 48.3% vs Grok 4 Heavy at 44.4%.