Compare · ModelsLive · 2 picked · head to head
internlm-20b vs Qwen-14B
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Qwen-14B wins on 3/6 benchmarks
Qwen-14B wins 3 of 6 shared benchmarks. Leads in knowledge · reasoning.
Category leads
knowledge·Qwen-14Breasoning·Qwen-14Bmath·internlm-20b
Hype vs Reality
Attention vs performance
internlm-20b
#52 by perf·no signal
Qwen-14B
#43 by perf·#2 by attention
Vendor risk
Who is behind the model
U
Unknown
private · undisclosed
Alibaba (Qwen)
$293.0B·Tier 1
Head to head
6 benchmarks · 2 models
internlm-20bQwen-14B
ARC AI2
Qwen-14B leads by +3.6
AI2 Reasoning Challenge · tests grade-school level science knowledge with multiple-choice questions requiring reasoning beyond simple retrieval.
internlm-20b
75.6
Qwen-14B
79.2
BBH
Qwen-14B leads by +3.3
BIG-Bench Hard · a curated subset of 23 challenging tasks from BIG-Bench where language models previously failed to outperform average humans.
internlm-20b
36.7
Qwen-14B
40.0
GSM8K
internlm-20b leads by +1.6
Grade School Math 8K · 8,500 linguistically diverse grade-school math word problems that require multi-step reasoning to solve.
internlm-20b
62.9
Qwen-14B
61.3
LAMBADA
internlm-20b leads by +0.7
LAMBADA · measures the ability to predict the final word of a passage, requiring broad contextual understanding across long text spans.
internlm-20b
71.8
Qwen-14B
71.1
MMLU
Qwen-14B leads by +20.4
Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge.
internlm-20b
34.7
Qwen-14B
55.1
PIQA
internlm-20b leads by +0.8
PIQA (Physical Interaction QA) · tests intuitive physical reasoning by asking models to select the correct approach for everyday physical tasks.
internlm-20b
60.6
Qwen-14B
59.8
Full benchmark table
| Benchmark | internlm-20b | Qwen-14B |
|---|---|---|
ARC AI2 AI2 Reasoning Challenge · tests grade-school level science knowledge with multiple-choice questions requiring reasoning beyond simple retrieval. | 75.6 | 79.2 |
BBH BIG-Bench Hard · a curated subset of 23 challenging tasks from BIG-Bench where language models previously failed to outperform average humans. | 36.7 | 40.0 |
GSM8K Grade School Math 8K · 8,500 linguistically diverse grade-school math word problems that require multi-step reasoning to solve. | 62.9 | 61.3 |
LAMBADA LAMBADA · measures the ability to predict the final word of a passage, requiring broad contextual understanding across long text spans. | 71.8 | 71.1 |
MMLU Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge. | 34.7 | 55.1 |
PIQA PIQA (Physical Interaction QA) · tests intuitive physical reasoning by asking models to select the correct approach for everyday physical tasks. | 60.6 | 59.8 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
U internlm-20b | — | — | — | — |
| — | — | — | — |