Qwen3.7-MaxvsGrok 4.20 Beta
Qwen3.7-Max | Grok 4.20 Beta | |
|---|---|---|
| API pricingUSD per 1M tokens · lower wins · base tier | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | $2.50 | $1.25 |
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. | $7.50 | $2.50 |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | — | $0.20 |
| Benchmarks | ||
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. | 72% | 56% |
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. | 80.4% | 76.7% |
| BenchmarksPublished by one model only | ||
SWE-Bench ProAgentic coding — Can the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better. | 60.6% | — |
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. | 91.6% | — |
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. | 69.7% | — |
MCP AtlasMulti-step tool use — Can the AI chain together many tools and steps to complete one bigger task, rather than doing just a single thing? Higher is better. | 76.4% | — |
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. | 41.4% | — |
ARC-AGI-2Abstract reasoning — Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. | — | 53.3% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 92.4% | — |
| Overview | ||
| Company | Qwen | SpaceXAI |
| Release date | May 20 2026 | Feb 17 2026 |
| Access | Proprietary | Proprietary |
Other comparisons
Qwen3.7-MaxvsClaude Fable 5.1Grok 4.20 BetavsClaude Fable 5.1Qwen3.7-MaxvsGPT-6 AstraGrok 4.20 BetavsGPT-6 AstraQwen3.7-MaxvsGemini 3.8 FlashGrok 4.20 BetavsGemini 3.8 FlashQwen3.7-MaxvsMuse Spark 1.3Grok 4.20 BetavsMuse Spark 1.3Qwen3.7-MaxvsDeepSeek-V4.1-FlashGrok 4.20 BetavsDeepSeek-V4.1-FlashQwen3.7-MaxvsMistral Medium 3.5Grok 4.20 BetavsMistral Medium 3.5
Frequently asked questions
Qwen3.7-Max leads Grok 4.20 Beta on 2 of the 2 benchmarks they both report (BullshitBench v2, SWE-Bench Verified). Grok 4.20 Beta is cheaper on both input and output: $1.25 vs $2.50 per million input tokens, and $2.50 vs $7.50 per million output tokens. Figures are base-tier rates. Grok 4.20 Beta shipped 92 days before Qwen3.7-Max, so benchmark comparisons should account for the intervening progress.
Published specifications for these two models are limited — see each model page for the latest details.
On BullshitBench v2, Qwen3.7-Max leads at 72% vs Grok 4.20 Beta at 56%. On SWE-Bench Verified, Qwen3.7-Max leads at 80.4% vs Grok 4.20 Beta at 76.7%.