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