Compare · ModelsLive · 2 picked · head to head
Falcon-180B vs Gemma 2 27B
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Gemma 2 27B wins on 8/9 benchmarks
Gemma 2 27B wins 8 of 9 shared benchmarks. Leads in math · general · knowledge.
Category leads
math·Gemma 2 27Bgeneral·Gemma 2 27Bknowledge·Gemma 2 27Blanguage·Gemma 2 27Breasoning·Gemma 2 27B
Hype vs Reality
Attention vs performance
Falcon-180B
#164 by perf·no signal
Gemma 2 27B
#220 by perf·#7 by attention
Vendor risk
Who is behind the model
TII
private · undisclosed
Google DeepMind
$4.20T·Tier 1
Head to head
9 benchmarks · 2 models
Falcon-180BGemma 2 27B
GSM8K
Gemma 2 27B leads by +30.5
Grade School Math 8K · 8,500 linguistically diverse grade-school math word problems that require multi-step reasoning to solve.
Falcon-180B
54.4
Gemma 2 27B
84.9
BBH (HuggingFace)
Gemma 2 27B leads by +27.3
Falcon-180B
21.9
Gemma 2 27B
49.3
GPQA
Gemma 2 27B leads by +13.9
Falcon-180B
2.8
Gemma 2 27B
16.7
IFEval
Gemma 2 27B leads by +47.2
Falcon-180B
32.6
Gemma 2 27B
79.8
MATH Level 5
Gemma 2 27B leads by +21.1
Falcon-180B
2.8
Gemma 2 27B
23.9
MMLU-PRO
Gemma 2 27B leads by +22.9
Falcon-180B
15.4
Gemma 2 27B
38.4
MUSR
Gemma 2 27B leads by +1.6
Falcon-180B
7.5
Gemma 2 27B
9.1
MMLU
Gemma 2 27B leads by +6.8
Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge.
Falcon-180B
60.8
Gemma 2 27B
67.6
PIQA
Falcon-180B leads by +2.4
PIQA (Physical Interaction QA) · tests intuitive physical reasoning by asking models to select the correct approach for everyday physical tasks.
Falcon-180B
69.8
Gemma 2 27B
67.4
Full benchmark table
| Benchmark | Falcon-180B | Gemma 2 27B |
|---|---|---|
GSM8K Grade School Math 8K · 8,500 linguistically diverse grade-school math word problems that require multi-step reasoning to solve. | 54.4 | 84.9 |
BBH (HuggingFace) | 21.9 | 49.3 |
GPQA | 2.8 | 16.7 |
IFEval | 32.6 | 79.8 |
MATH Level 5 | 2.8 | 23.9 |
MMLU-PRO | 15.4 | 38.4 |
MUSR | 7.5 | 9.1 |
MMLU Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge. | 60.8 | 67.6 |
PIQA PIQA (Physical Interaction QA) · tests intuitive physical reasoning by asking models to select the correct approach for everyday physical tasks. | 69.8 | 67.4 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| — | — | — | — | |
| $0.65 | $0.65 | 8K tokens (~4 books) | $6.50 |