# MAI-Thinking-1 vs Beam 1.0 501B-A23B NVFP4

> Side-by-side benchmark comparison for MAI-Thinking-1 and Beam 1.0 501B-A23B NVFP4 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/mai-thinking-1-vs-reflection-beam-nvfp4
- Last updated: October 16, 2026

- Shared sourced benchmarks: 5
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Beam 1.0 501B-A23B NVFP4 leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- Beam 1.0 501B-A23B NVFP4 has the higher overall point estimate 70 to 53.16. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in instruction following, where the averages are 94.7 for MAI-Thinking-1 and 86.2 for Beam 1.0 501B-A23B NVFP4.
- The biggest single benchmark swing is SWE-bench Pro in Coding, with scores of 52.8% and 65.6%.
- Beam 1.0 501B-A23B NVFP4 also has the larger context window at 1M.

## Model Snapshot

| Property | MAI-Thinking-1 | Beam 1.0 501B-A23B NVFP4 |
|----------|----------|----------|
| Creator | Microsoft | Reflection AI |
| Type | Proprietary | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 256K | 1M |
| Overall Score | 53.16 | null |
| Benchmarks Covered | 13 | 19 |
| Pricing (input/output) | N/A | Pricing unavailable / Pricing unavailable |

## Category Breakdown

### Agentic

- Winner: Not comparable
- MAI-Thinking-1 public-lane score: Coming soon
- Beam 1.0 501B-A23B NVFP4 public-lane score: Coming soon

| Benchmark | MAI-Thinking-1 | Beam 1.0 501B-A23B NVFP4 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 46% | Coming soon | Coming soon |
| τ³-bench results | Coming soon | 35.4% | Coming soon |
| HLE w/ tools | Coming soon | 51.1% | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 78.4% | Coming soon |
| MCP Atlas | Coming soon | 80.5% | Coming soon |
| BrowseComp | Coming soon | 75.6% | Coming soon |
| DeepSearchQA | Coming soon | 81.1% | Coming soon |

### Coding

- Winner: Not comparable
- MAI-Thinking-1 public-lane score: Coming soon
- Beam 1.0 501B-A23B NVFP4 public-lane score: Coming soon

| Benchmark | MAI-Thinking-1 | Beam 1.0 501B-A23B NVFP4 | Winner |
|-----------|-----------|-----------|--------|
| LiveCodeBench v6 | 87.7% | Coming soon | Coming soon |
| SWE-bench Verified | 73.5% | 80.7% | Beam 1.0 501B-A23B NVFP4 |
| SWE-bench Pro | 52.8% | 65.6% | Beam 1.0 501B-A23B NVFP4 |
| Terminal-Bench 2.0 | 46.0% | Coming soon | Coming soon |
| DeepSWE | Coming soon | 42.7% | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 78.4% | Coming soon |
| SWE-Atlas Codebase QnA | Coming soon | 31.4% | Coming soon |
| SWE Multilingual | Coming soon | 77.5% | Coming soon |
| SciCode | Coming soon | 46.9% | Coming soon |

### Reasoning

- Winner: Not comparable
- MAI-Thinking-1 public-lane score: Coming soon
- Beam 1.0 501B-A23B NVFP4 public-lane score: 85.5 (Unranked · 3 rankable rows)

| Benchmark | MAI-Thinking-1 | Beam 1.0 501B-A23B NVFP4 | Winner |
|-----------|-----------|-----------|--------|
| Graphwalks BFS 128K | 90% | Coming soon | Coming soon |
| CritPt | Coming soon | 15.4% | Coming soon |
| LongBench v2 | Coming soon | 67.2% | Coming soon |

### Knowledge

- Winner: Not comparable
- MAI-Thinking-1 public-lane score: 55.5 (Estimated · #57/184)
- Beam 1.0 501B-A23B NVFP4 public-lane score: Coming soon

| Benchmark | MAI-Thinking-1 | Beam 1.0 501B-A23B NVFP4 | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 84.2% | Coming soon | Coming soon |
| GPQA-D | 84.2% | 89.3% | Beam 1.0 501B-A23B NVFP4 |
| MMLU-Pro | 85% | Coming soon | Coming soon |
| HLE w/o tools | Coming soon | 34.8% | Coming soon |

### Instruction Following

- Winner: MAI-Thinking-1
- MAI-Thinking-1 public-lane score: 94.7 (#3/148)
- Beam 1.0 501B-A23B NVFP4 public-lane score: 86.2 (#44/148)

| Benchmark | MAI-Thinking-1 | Beam 1.0 501B-A23B NVFP4 | Winner |
|-----------|-----------|-----------|--------|
| IFBench | 85% | 79.2% | MAI-Thinking-1 |

### Mathematics

- Winner: Not comparable
- MAI-Thinking-1 public-lane score: 81.1 (Unranked · 3 rankable rows)
- Beam 1.0 501B-A23B NVFP4 public-lane score: 87.9 (Unranked · 1 rankable row)

| Benchmark | MAI-Thinking-1 | Beam 1.0 501B-A23B NVFP4 | Winner |
|-----------|-----------|-----------|--------|
| AIME 2025 | 97% | Coming soon | Coming soon |
| AIME26 | 94.5% | 97.5% | Beam 1.0 501B-A23B NVFP4 |
| HMMT Feb 2026 | 84.9% | Coming soon | Coming soon |

## FAQ

### Which is better overall, MAI-Thinking-1 or Beam 1.0 501B-A23B NVFP4?

Beam 1.0 501B-A23B NVFP4 has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between MAI-Thinking-1 and Beam 1.0 501B-A23B NVFP4?

The widest category gap is in instruction following, where the averages are 94.7 for MAI-Thinking-1 and 86.2 for Beam 1.0 501B-A23B NVFP4.

### How many benchmarks does MAI-Thinking-1 cover on BenchLM?

MAI-Thinking-1 currently has 13 sourced benchmark scores on BenchLM.

### How many benchmarks does Beam 1.0 501B-A23B NVFP4 cover on BenchLM?

Beam 1.0 501B-A23B NVFP4 currently has 19 sourced benchmark scores on BenchLM.

## Related Comparisons

- [MAI-Thinking-1 vs Beam 1.0 501B-A23B](/compare/mai-thinking-1-vs-reflection-beam)
- [Beam 1.0 501B-A23B NVFP4 vs Beam 1.0 501B-A23B](/compare/reflection-beam-vs-reflection-beam-nvfp4)
- [MAI-Thinking-1 vs Beam 1.0 501B-A23B FP8](/compare/mai-thinking-1-vs-reflection-beam-fp8)
- [Beam 1.0 501B-A23B NVFP4 vs Beam 1.0 501B-A23B FP8](/compare/reflection-beam-fp8-vs-reflection-beam-nvfp4)

## Explore More

- [MAI-Thinking-1 profile](/models/mai-thinking-1)
- [Beam 1.0 501B-A23B NVFP4 profile](/models/reflection-beam-nvfp4)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)