# LFM3-1.7B vs Qwen3 235B 2507 (Reasoning)

> Side-by-side benchmark comparison for LFM3-1.7B and Qwen3 235B 2507 (Reasoning) across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/lfm3-1-7b-vs-qwen3-235b-2507-reasoning
- Last updated: October 27, 2026

- Shared sourced benchmarks: 4
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Qwen3 235B 2507 (Reasoning) leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- Qwen3 235B 2507 (Reasoning) has the higher overall point estimate 62 to 22.99. Conditional score ranges do not establish rank confidence.
- The biggest single benchmark swing is GPQA in Knowledge, with scores of 63.4% and 81.1%.
- LFM3-1.7B also has the larger context window at 256K.

## Model Snapshot

| Property | LFM3-1.7B | Qwen3 235B 2507 (Reasoning) |
|----------|----------|----------|
| Creator | LiquidAI | Alibaba |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 256K | 128K |
| Overall Score | 22.99 | null |
| Benchmarks Covered | 24 | 8 |
| Pricing (input/output) | $0.00 / $0.00 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Not comparable
- LFM3-1.7B public-lane score: 14.4 (Estimated · #123/134)
- Qwen3 235B 2507 (Reasoning) public-lane score: Coming soon

| Benchmark | LFM3-1.7B | Qwen3 235B 2507 (Reasoning) | Winner |
|-----------|-----------|-----------|--------|
| AutomationBench | 41.3% | Coming soon | Coming soon |
| BFCL v4 | 71.4% | Coming soon | Coming soon |
| τ³-bench results | 68.0% | Coming soon | Coming soon |
| WebArena-Verified | 38.4% | Coming soon | Coming soon |
| MCP Atlas | 32.6% | Coming soon | Coming soon |
| ToolSandbox | 80.36% | Coming soon | Coming soon |
| Claw-Eval | 68.6% | Coming soon | Coming soon |
| HLE w/ tools | 13.9% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 12.9% | Coming soon | Coming soon |
| LiveClaw | 45.60% | Coming soon | Coming soon |

### Coding

- Winner: Not comparable
- LFM3-1.7B public-lane score: 13 (Estimated · #142/155)
- Qwen3 235B 2507 (Reasoning) public-lane score: Coming soon

| Benchmark | LFM3-1.7B | Qwen3 235B 2507 (Reasoning) | Winner |
|-----------|-----------|-----------|--------|
| SciCode | 28.5% | Coming soon | Coming soon |
| SWE-bench Verified | 43.4% | Coming soon | Coming soon |
| SWE Multilingual | 23% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 12.9% | Coming soon | Coming soon |
| LiveCodeBench v6 | 73.5% | 74.1% | Qwen3 235B 2507 (Reasoning) |
| LiveCodeBench Pro | 31.7% | Coming soon | Coming soon |

### Reasoning

- Winner: Not comparable
- LFM3-1.7B public-lane score: 61.3 (Unranked · 1 rankable row)
- Qwen3 235B 2507 (Reasoning) public-lane score: Coming soon

| Benchmark | LFM3-1.7B | Qwen3 235B 2507 (Reasoning) | Winner |
|-----------|-----------|-----------|--------|
| RULER (128K) | 65.56% | Coming soon | Coming soon |

### Knowledge

- Winner: Not comparable
- LFM3-1.7B public-lane score: 25.5 (Estimated · #175/189)
- Qwen3 235B 2507 (Reasoning) public-lane score: Coming soon

| Benchmark | LFM3-1.7B | Qwen3 235B 2507 (Reasoning) | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 63.4% | 81.1% | Qwen3 235B 2507 (Reasoning) |
| GPQA-D | 63.4% | Coming soon | Coming soon |
| HLE | 7.2% | 18.2% | Qwen3 235B 2507 (Reasoning) |
| SuperGPQA | Coming soon | 64.9% | Coming soon |
| MMLU-Pro | Coming soon | 84.4% | Coming soon |

### Multilingual

- Winner: Not comparable
- LFM3-1.7B public-lane score: Coming soon
- Qwen3 235B 2507 (Reasoning) public-lane score: 83.8 (#12/17)

| Benchmark | LFM3-1.7B | Qwen3 235B 2507 (Reasoning) | Winner |
|-----------|-----------|-----------|--------|
| MMLU-ProX | Coming soon | 81% | Coming soon |

### Instruction Following

- Winner: Not comparable
- LFM3-1.7B public-lane score: 71.7 (#76/156)
- Qwen3 235B 2507 (Reasoning) public-lane score: Coming soon

| Benchmark | LFM3-1.7B | Qwen3 235B 2507 (Reasoning) | Winner |
|-----------|-----------|-----------|--------|
| IFEval | 96.7% | 87.8% | LFM3-1.7B |
| IFBench | 73.0% | Coming soon | Coming soon |
| Multi-IF | 89.10% | Coming soon | Coming soon |
| IFStruct | 93.72% | Coming soon | Coming soon |

### Mathematics

- Winner: Not comparable
- LFM3-1.7B public-lane score: Coming soon
- Qwen3 235B 2507 (Reasoning) public-lane score: Coming soon

| Benchmark | LFM3-1.7B | Qwen3 235B 2507 (Reasoning) | Winner |
|-----------|-----------|-----------|--------|
| AIME 2025 | Coming soon | 92.3% | Coming soon |

## FAQ

### Which is better overall, LFM3-1.7B or Qwen3 235B 2507 (Reasoning)?

Qwen3 235B 2507 (Reasoning) has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### How many benchmarks does LFM3-1.7B cover on BenchLM?

LFM3-1.7B currently has 24 sourced benchmark scores on BenchLM.

### How many benchmarks does Qwen3 235B 2507 (Reasoning) cover on BenchLM?

Qwen3 235B 2507 (Reasoning) currently has 8 sourced benchmark scores on BenchLM.

## Related Comparisons

- [LFM3-1.7B vs LFM3-1.7B-Base](/compare/lfm3-1-7b-vs-lfm3-1-7b-base)
- [Qwen3 235B 2507 (Reasoning) vs LFM3-1.7B-Base](/compare/lfm3-1-7b-base-vs-qwen3-235b-2507-reasoning)
- [LFM3-1.7B vs LFM3-Audio-2B](/compare/lfm3-1-7b-vs-lfm3-audio-2b)
- [Qwen3 235B 2507 (Reasoning) vs LFM3-Audio-2B](/compare/lfm3-audio-2b-vs-qwen3-235b-2507-reasoning)

## Explore More

- [LFM3-1.7B profile](/models/lfm3-1-7b)
- [Qwen3 235B 2507 (Reasoning) profile](/models/qwen3-235b-2507-reasoning)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)