Compare · ModelsLive · 2 picked · head to head
Stable Beluga 2 vs internlm-20b
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Stable Beluga 2 wins on 6/7 benchmarks
Stable Beluga 2 wins 6 of 7 shared benchmarks. Leads in knowledge · reasoning · math.
Category leads
knowledge·Stable Beluga 2reasoning·Stable Beluga 2math·Stable Beluga 2
Hype vs Reality
Attention vs performance
Stable Beluga 2
#131 by perf·no signal
internlm-20b
#60 by perf·no signal
Vendor risk
Who is behind the model
U
Unknown
private · undisclosed
U
Unknown
private · undisclosed
Head to head
7 benchmarks · 2 models
Stable Beluga 2internlm-20b
ARC AI2
Stable Beluga 2 leads by +5.9
AI2 Reasoning Challenge · tests grade-school level science knowledge with multiple-choice questions requiring reasoning beyond simple retrieval.
Stable Beluga 2
81.5
internlm-20b
75.6
BBH
Stable Beluga 2 leads by +22.4
BIG-Bench Hard · a curated subset of 23 challenging tasks from BIG-Bench where language models previously failed to outperform average humans.
Stable Beluga 2
59.1
internlm-20b
36.7
GSM8K
Stable Beluga 2 leads by +6.7
Grade School Math 8K · 8,500 linguistically diverse grade-school math word problems that require multi-step reasoning to solve.
Stable Beluga 2
69.6
internlm-20b
62.9
HellaSwag
Stable Beluga 2 leads by +8.0
HellaSwag · tests commonsense reasoning by asking models to predict the most plausible continuation of everyday scenarios.
Stable Beluga 2
78.8
internlm-20b
70.8
LAMBADA
internlm-20b leads by +0.5
LAMBADA · measures the ability to predict the final word of a passage, requiring broad contextual understanding across long text spans.
Stable Beluga 2
71.3
internlm-20b
71.8
MMLU
Stable Beluga 2 leads by +23.5
Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge.
Stable Beluga 2
58.1
internlm-20b
34.7
PIQA
Stable Beluga 2 leads by +6.0
PIQA (Physical Interaction QA) · tests intuitive physical reasoning by asking models to select the correct approach for everyday physical tasks.
Stable Beluga 2
66.6
internlm-20b
60.6
Full benchmark table
| Benchmark | Stable Beluga 2 | internlm-20b |
|---|---|---|
ARC AI2 AI2 Reasoning Challenge · tests grade-school level science knowledge with multiple-choice questions requiring reasoning beyond simple retrieval. | 81.5 | 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. | 59.1 | 36.7 |
GSM8K Grade School Math 8K · 8,500 linguistically diverse grade-school math word problems that require multi-step reasoning to solve. | 69.6 | 62.9 |
HellaSwag HellaSwag · tests commonsense reasoning by asking models to predict the most plausible continuation of everyday scenarios. | 78.8 | 70.8 |
LAMBADA LAMBADA · measures the ability to predict the final word of a passage, requiring broad contextual understanding across long text spans. | 71.3 | 71.8 |
MMLU Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge. | 58.1 | 34.7 |
PIQA PIQA (Physical Interaction QA) · tests intuitive physical reasoning by asking models to select the correct approach for everyday physical tasks. | 66.6 | 60.6 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
U Stable Beluga 2 | — | — | — | — |
U internlm-20b | — | — | — | — |