Model comparison
Grok 4.20 vs MAI-Thinking-1
Head-to-head evidence from 4 shared benchmark results across 3 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: Grok 4.20 #88 (Estimated); MAI-Thinking-1 unranked (Not scored). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. Grok 4.20 and MAI-Thinking-1 share 4 comparable benchmark results. 2 of 8 categories are comparable. 14 results are unique to Grok 4.20; 9 to MAI-Thinking-1.
Updated July 23, 2026- Shared results
- 4
- Grok 4.20 only
- 14
- MAI-Thinking-1 only
- 9
- Comparable categories
- 2 / 8
Treat this as a split decision. Grok 4.20 makes more sense if coding is the priority or you need the larger 2M context window; MAI-Thinking-1 is the better fit if its strengths line up with your actual workload.
Confidence note. This is a partial-evidence comparison with 4 shared benchmark results across 3 evidence categories; 2 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
Grok 4.20 and MAI-Thinking-1 finish on the same BenchAlign overall score, so this is less about a single winner and more about where the edge shows up. The BenchAlign headline says tie; the benchmark table is where the real choice happens.
Grok 4.20 gives you the larger context window at 2M, compared with 256K for MAI-Thinking-1.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | Grok 4.20 | Δ | MAI-Thinking-1 |
|---|---|---|---|
| Coding | Grok 4.2067.1 | Margin← 1.6 | MAI-Thinking-165.5 |
| Agentic | Grok 4.2047.1 | Margin← 1.1 | MAI-Thinking-146.0 |
| Reasoning | Grok 4.2053.3 | MarginNo overlap | MAI-Thinking-1Not measured |
| Knowledge | Grok 4.20Not measured | MarginNo overlap | MAI-Thinking-172.5 |
| Math | Grok 4.20Not measured | MarginNo overlap | MAI-Thinking-189.7 |
| Multimodal | Grok 4.2070.1 | MarginNo overlap | MAI-Thinking-1Not measured |
| Inst. Following | Grok 4.20Not measured | MarginNo overlap | MAI-Thinking-185.0 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
SWE-bench Verified
CodingA 76.7%B 73.5%Winner: Grok 4.20Δ 3.2SWE-bench Verified: Grok 4.20 scored 76.7%; MAI-Thinking-1 scored 73.5%. Grok 4.20 wins this benchmark. - Source ↗
Terminal-Bench 2.0
AgenticA 47.1%B 46%Winner: Grok 4.20Δ 1.1Terminal-Bench 2.0: Grok 4.20 scored 47.1%; MAI-Thinking-1 scored 46%. Grok 4.20 wins this benchmark. - Source ↗
SWE-bench Pro
CodingA 51.8%B 52.8%Winner: MAI-Thinking-1Δ 1SWE-bench Pro: Grok 4.20 scored 51.8%; MAI-Thinking-1 scored 52.8%. MAI-Thinking-1 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | Grok 4.20 | MAI-Thinking-1 | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | Grok 4.20$2 input / $6 output | MAI-Thinking-1Not available | A complete price comparison is not available. |
| Generation speedtokens per second | Grok 4.20233 tok/s | MAI-Thinking-1Not available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | Grok 4.2010.33 s | MAI-Thinking-1Not available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | Grok 4.202M | MAI-Thinking-1256K | Grok 4.20 lists the larger context window. |
Benchmark Deep Dive
AgenticGrok 4.20 wins3 benchmarks
CodingGrok 4.20 wins5 benchmarks
Reasoning2 benchmarks
Knowledge7 benchmarks
| Benchmark | Grok 4.20 | MAI-Thinking-1 | Result |
|---|---|---|---|
| GPQA-DSource | 88.5% | 84.2% | Grok 4.20 leads |
| HLE w/o toolsSource | 31.6% | — | Not comparable |
| HealthBench HardSource | 20.3% | — | Not comparable |
| MedXpertQA (Text)Source | 50.2% | — | Not comparable |
| GPQASource | — | 84.2% | Not comparable |
| MMLU-ProSource | — | 85% | Not comparable |
| SimpleQASource | — | 31% | Not comparable |
Math3 benchmarks
Multimodal6 benchmarks
Inst. Following1 benchmarks
| Benchmark | Grok 4.20 | MAI-Thinking-1 | Result |
|---|---|---|---|
| IFBenchSource | — | 85% | Not comparable |
Frequently Asked Questions (3)
Which is better, Grok 4.20 or MAI-Thinking-1?
Grok 4.20 and MAI-Thinking-1 are tied on the BenchAlign overall score, so the right pick depends on which category matters most for your use case.
Which is better for coding, Grok 4.20 or MAI-Thinking-1?
Grok 4.20 has the edge for coding in this comparison, averaging 67.1 versus 65.5. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, Grok 4.20 or MAI-Thinking-1?
Grok 4.20 has the edge for agentic tasks in this comparison, averaging 47.1 versus 46. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Related Comparisons
Explore More
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.