Model comparison
INTELLECT-1 vs Qwen2.5 7B Instruct
Qwen2.5 7B Instruct has enough public results to be ranked (#314); INTELLECT-1 does not yet, so treat this comparison as directional.
Last verified . 2 shared benchmarks.
Hugging Face
Alibaba (Qwen)Summary
- They share 2 benchmarks with published results for both.
- Qwen2.5 7B Instruct has downloadable open weights; the other is API-only.
Side by side
| INTELLECT-1 | Qwen2.5 7B Instruct | |
|---|---|---|
| Provider | Hugging Face | Alibaba (Qwen) |
| Noometry Index | — | 28.6 |
| Released | 2024-11-29 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.17 |
| Output $ / M tokens | — | $0.70 |
| Results tracked | 7 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
INTELLECT-1: —, Qwen2.5 7B Instruct: 35.9 (#204)
| Benchmark | INTELLECT-1 | Qwen2.5 7B Instruct |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| BigCodeBench Complete | — | 46.1% |
Agentic & Tool Use Not comparable
INTELLECT-1: —, Qwen2.5 7B Instruct: 23.5 (#117)
| Benchmark | INTELLECT-1 | Qwen2.5 7B Instruct |
|---|---|---|
| BALROG | — | 7.8% |
Reasoning Not comparable
INTELLECT-1: —, Qwen2.5 7B Instruct: 14.3 (#317)
| Benchmark | INTELLECT-1 | Qwen2.5 7B Instruct |
|---|---|---|
| Epoch Capabilities Index | 100.38 | 118.44 |
| Chess Puzzles | — | 0% |
| DTBench | — | 47.7% |
| LMCA | — | 6.4% |
| BIG-Bench Hard | 34.9% | — |
| HellaSwag | 71.4% | — |
| WinoGrande | 65.8% | — |
Math Not comparable
INTELLECT-1: —, Qwen2.5 7B Instruct: 11.8 (#300)
| Benchmark | INTELLECT-1 | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.5% |
| Omni-MATH | — | 29.4% |
| GSM8K | 38.6% | — |
Knowledge Not comparable
INTELLECT-1: —, Qwen2.5 7B Instruct: 17.0 (#281)
| Benchmark | INTELLECT-1 | Qwen2.5 7B Instruct |
|---|---|---|
| MMLU | 49.9% | 72.9% |
| GPQA Diamond | — | 35.5% |
| MMLU-Pro | — | 53.9% |
| GPQA (HELM) | — | 34.1% |
| ARC (AI2) Challenge | 54.5% | — |
Instruction Following Not comparable
INTELLECT-1: —, Qwen2.5 7B Instruct: 63.4 (#226)
| Benchmark | INTELLECT-1 | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | — | 74.1% |
Writing & Preference Not comparable
INTELLECT-1: —, Qwen2.5 7B Instruct: 48.8 (#194)
| Benchmark | INTELLECT-1 | Qwen2.5 7B Instruct |
|---|---|---|
| WildBench | — | 73.1% |
Frequently asked questions
Is INTELLECT-1 better than Qwen2.5 7B Instruct?
Qwen2.5 7B Instruct has enough public results to be ranked (#314); INTELLECT-1 does not yet, so treat this comparison as directional.
How many benchmarks do INTELLECT-1 and Qwen2.5 7B Instruct share?
2 benchmarks have published results for both models. INTELLECT-1 has 7 scored results on Noometry and Qwen2.5 7B Instruct has 15.