Model comparison
Grok Build 0.1 vs Qwen3-1.7B
Grok Build 0.1 is the stronger model overall, scoring 36.4 to 26.6 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)Summary
- The widest gap is in reasoning, where Grok Build 0.1 leads 32.2 to 19.2.
- Qwen3-1.7B has downloadable open weights; the other is API-only.
Side by side
| Grok Build 0.1 | Qwen3-1.7B | |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 36.4 | 26.6 |
| Released | 2026-04-16 | 2025-04-29 |
| Weights | Proprietary | Open |
| Context window | 256K | — |
| Max output | 256K | — |
| Input $ / M tokens | $1 | — |
| Output $ / M tokens | $2 | — |
| Results tracked | 3 | 4 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Grok Build 0.1: 43.1 (#91), Qwen3-1.7B: —
| Benchmark | Grok Build 0.1 | Qwen3-1.7B |
|---|---|---|
| SciCode | 50.2% | — |
Agentic & Tool Use Qwen3-1.7B leads
Grok Build 0.1: 22.7 (#129), Qwen3-1.7B: 24.7 (#115)
| Benchmark | Grok Build 0.1 | Qwen3-1.7B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.4% |
| GBAEval | 2.4% | — |
Reasoning Grok Build 0.1 leads
Grok Build 0.1: 32.2 (#77), Qwen3-1.7B: 19.2 (#267)
| Benchmark | Grok Build 0.1 | Qwen3-1.7B |
|---|---|---|
| CritPt | 9.1% | — |
| Chess Puzzles | — | 0% |
Math Not comparable
Grok Build 0.1: —, Qwen3-1.7B: 16.3 (#294)
| Benchmark | Grok Build 0.1 | Qwen3-1.7B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 8.1% |
Knowledge Not comparable
Grok Build 0.1: —, Qwen3-1.7B: 19.6 (#278)
| Benchmark | Grok Build 0.1 | Qwen3-1.7B |
|---|---|---|
| GPQA Diamond | — | 38% |
Frequently asked questions
Is Grok Build 0.1 better than Qwen3-1.7B?
Grok Build 0.1 is the stronger model overall, scoring 36.4 to 26.6 on the Noometry Index.
How many benchmarks do Grok Build 0.1 and Qwen3-1.7B share?
0 benchmarks have published results for both models. Grok Build 0.1 has 3 scored results on Noometry and Qwen3-1.7B has 4.