Compare · ModelsLive · 2 picked · head to head
RedPajama-INCITE-7B-Base vs Phi-1.5
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Phi-1.5 wins on 8/11 benchmarks
Phi-1.5 wins 8 of 11 shared benchmarks. Leads in knowledge · general · math.
Category leads
knowledge·Phi-1.5general·Phi-1.5language·RedPajama-INCITE-7B-Basemath·Phi-1.5reasoning·Phi-1.5
Hype vs Reality
Attention vs performance
RedPajama-INCITE-7B-Base
#257 by perf·no signal
Phi-1.5
#260 by perf·no signal
Vendor risk
Who is behind the model
U
Unknown
private · undisclosed
Microsoft
$3.00T·Big Tech
Head to head
11 benchmarks · 2 models
RedPajama-INCITE-7B-BasePhi-1.5
ARC AI2
Phi-1.5 leads by +7.1
AI2 Reasoning Challenge · tests grade-school level science knowledge with multiple-choice questions requiring reasoning beyond simple retrieval.
RedPajama-INCITE-7B-Base
18.8
Phi-1.5
25.9
HellaSwag
RedPajama-INCITE-7B-Base leads by +30.3
HellaSwag · tests commonsense reasoning by asking models to predict the most plausible continuation of everyday scenarios.
RedPajama-INCITE-7B-Base
60.4
Phi-1.5
30.1
BBH (HuggingFace)
Phi-1.5 leads by +2.4
RedPajama-INCITE-7B-Base
5.1
Phi-1.5
7.5
GPQA
Phi-1.5 leads by +1.7
RedPajama-INCITE-7B-Base
0.7
Phi-1.5
2.4
IFEval
RedPajama-INCITE-7B-Base leads by +0.5
RedPajama-INCITE-7B-Base
20.8
Phi-1.5
20.3
MATH Level 5
Phi-1.5 leads by +0.2
RedPajama-INCITE-7B-Base
1.6
Phi-1.5
1.8
MMLU-PRO
Phi-1.5 leads by +5.5
RedPajama-INCITE-7B-Base
2.2
Phi-1.5
7.7
MUSR
Phi-1.5 leads by +0.4
RedPajama-INCITE-7B-Base
3.0
Phi-1.5
3.4
MMLU
Phi-1.5 leads by +15.1
Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge.
RedPajama-INCITE-7B-Base
1.7
Phi-1.5
16.8
OpenBookQA
RedPajama-INCITE-7B-Base leads by +3.7
OpenBookQA · science questions that require combining a given core fact with broad common knowledge, mimicking an open-book exam setting.
RedPajama-INCITE-7B-Base
20.0
Phi-1.5
16.3
Winogrande
Phi-1.5 leads by +19.2
WinoGrande · large-scale commonsense reasoning benchmark where models must resolve ambiguous pronouns in carefully constructed sentence pairs.
RedPajama-INCITE-7B-Base
27.6
Phi-1.5
46.8
Full benchmark table
| Benchmark | RedPajama-INCITE-7B-Base | Phi-1.5 |
|---|---|---|
ARC AI2 AI2 Reasoning Challenge · tests grade-school level science knowledge with multiple-choice questions requiring reasoning beyond simple retrieval. | 18.8 | 25.9 |
HellaSwag HellaSwag · tests commonsense reasoning by asking models to predict the most plausible continuation of everyday scenarios. | 60.4 | 30.1 |
BBH (HuggingFace) | 5.1 | 7.5 |
GPQA | 0.7 | 2.4 |
IFEval | 20.8 | 20.3 |
MATH Level 5 | 1.6 | 1.8 |
MMLU-PRO | 2.2 | 7.7 |
MUSR | 3.0 | 3.4 |
MMLU Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge. | 1.7 | 16.8 |
OpenBookQA OpenBookQA · science questions that require combining a given core fact with broad common knowledge, mimicking an open-book exam setting. | 20.0 | 16.3 |
Winogrande WinoGrande · large-scale commonsense reasoning benchmark where models must resolve ambiguous pronouns in carefully constructed sentence pairs. | 27.6 | 46.8 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
U RedPajama-INCITE-7B-Base | — | — | — | — |
| — | — | — | — |