Compare · ModelsLive · 2 picked · head to head
Stable Beluga 2 vs Dolphin 2.9.1 Yi 1.5 34b
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Dolphin 2.9.1 Yi 1.5 34b wins on 5/6 benchmarks
Dolphin 2.9.1 Yi 1.5 34b wins 5 of 6 shared benchmarks. Leads in general · knowledge · language.
Category leads
general·Dolphin 2.9.1 Yi 1.5 34bknowledge·Dolphin 2.9.1 Yi 1.5 34blanguage·Dolphin 2.9.1 Yi 1.5 34bmath·Dolphin 2.9.1 Yi 1.5 34breasoning·Stable Beluga 2
Hype vs Reality
Attention vs performance
Stable Beluga 2
#102 by perf·no signal
Dolphin 2.9.1 Yi 1.5 34b
#193 by perf·no signal
Vendor risk
Who is behind the model
U
Unknown
private · undisclosed
D
DPHN
private · undisclosed
Head to head
6 benchmarks · 2 models
Stable Beluga 2Dolphin 2.9.1 Yi 1.5 34b
BBH (HuggingFace)
Dolphin 2.9.1 Yi 1.5 34b leads by +2.9
Stable Beluga 2
41.3
Dolphin 2.9.1 Yi 1.5 34b
44.2
GPQA
Dolphin 2.9.1 Yi 1.5 34b leads by +3.6
Stable Beluga 2
8.8
Dolphin 2.9.1 Yi 1.5 34b
12.4
IFEval
Dolphin 2.9.1 Yi 1.5 34b leads by +0.7
Stable Beluga 2
37.9
Dolphin 2.9.1 Yi 1.5 34b
38.5
MATH Level 5
Dolphin 2.9.1 Yi 1.5 34b leads by +14.3
Stable Beluga 2
4.4
Dolphin 2.9.1 Yi 1.5 34b
18.7
MMLU-PRO
Dolphin 2.9.1 Yi 1.5 34b leads by +13.3
Stable Beluga 2
25.9
Dolphin 2.9.1 Yi 1.5 34b
39.1
MUSR
Stable Beluga 2 leads by +1.7
Stable Beluga 2
18.6
Dolphin 2.9.1 Yi 1.5 34b
17.0
Full benchmark table
| Benchmark | Stable Beluga 2 | Dolphin 2.9.1 Yi 1.5 34b |
|---|---|---|
BBH (HuggingFace) | 41.3 | 44.2 |
GPQA | 8.8 | 12.4 |
IFEval | 37.9 | 38.5 |
MATH Level 5 | 4.4 | 18.7 |
MMLU-PRO | 25.9 | 39.1 |
MUSR | 18.6 | 17.0 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
U Stable Beluga 2 | — | — | — | — |
D Dolphin 2.9.1 Yi 1.5 34b | — | — | — | — |