Model comparison

Falcon-40B vs Gemini 3.7 Flash

Gemini 3.7 Flash has enough public results to be ranked (#11); Falcon-40B does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

Summary

  • They share 1 benchmark with published results for both.
  • Falcon-40B has downloadable open weights; the other is API-only.

Side by side

Falcon-40B and Gemini 3.7 Flash specifications
Falcon-40BGemini 3.7 Flash
ProviderTechnology Innovation InstituteGoogle
Noometry Index—59.8
Released2023-03-152026-08-13
WeightsOpenProprietary
Context window—1.05M
Max output—66K
Input $ / M tokens—$0.75
Output $ / M tokens—$3.75
Results tracked1244

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Not comparable

Falcon-40B: —, Gemini 3.7 Flash: 55.7 (#19)

Coding benchmarks
BenchmarkFalcon-40BGemini 3.7 Flash
DeepSWE—65.5%
FrontierCode—43.6%
LMArena WebDev—1593
FrontierSWE—20.3%
SciCode—59.8%
LMArena Coding—1499
ALE-Bench—904.3

Agentic & Tool Use Not comparable

Falcon-40B: —, Gemini 3.7 Flash: 42.2 (#18)

Agentic & Tool Use benchmarks
BenchmarkFalcon-40BGemini 3.7 Flash
APEX-Agents—67.8%
Remote Labor Index—5%
GDP.pdf—23.8%

Reasoning Not comparable

Falcon-40B: —, Gemini 3.7 Flash: 70.1 (#12)

Reasoning benchmarks
BenchmarkFalcon-40BGemini 3.7 Flash
Epoch Capabilities Index104.04157.72
ARC-AGI-2—84.6%
NYT Connections (extended)—94%
ARC-AGI-1—95.5%
CritPt—14.3%
Chess Puzzles—47%
LMArena Hard Prompts—1497
Mystery Game Puzzles—37%
DTBench—96.8%
LMCA—50.4%
BIG-Bench Hard37.1%—
HellaSwag85.3%—
LAMBADA77.3%—
PIQA83%—
WinoGrande76.9%—

Math Not comparable

Falcon-40B: —, Gemini 3.7 Flash: 69.5 (#18)

Math benchmarks
BenchmarkFalcon-40BGemini 3.7 Flash
FrontierMath (Tiers 1-3)—71.6%
FrontierMath Tier 4—36.6%
OTIS Mock AIME 2024-2025—97.2%
ProofBench—58%
LMArena Math—1511
GSM8K33.8%—

Knowledge Not comparable

Falcon-40B: —, Gemini 3.7 Flash: 69.8 (#4)

Knowledge benchmarks
BenchmarkFalcon-40BGemini 3.7 Flash
GPQA Diamond—94.8%
SimpleQA Verified—69.2%
LMArena Expert—1508
ARC (AI2) Challenge61.9%—
BoolQ83.1%—
MMLU56.9%—
OpenBookQA56.6%—
TriviaQA79.9%—

Multimodal Not comparable

Falcon-40B: —, Gemini 3.7 Flash: 36.9 (#69)

Multimodal benchmarks
BenchmarkFalcon-40BGemini 3.7 Flash
LMArena Vision—1314
Furniture Assembly—26.7%

Multilingual Not comparable

Falcon-40B: —, Gemini 3.7 Flash: 57.8 (#7)

Multilingual benchmarks
BenchmarkFalcon-40BGemini 3.7 Flash
LMArena Non-English—1485
LMArena Chinese—1553
LMArena French—1512
LMArena German—1485
LMArena Japanese—1506
LMArena Korean—1486
LMArena Russian—1519
LMArena Spanish—1507

Instruction Following Not comparable

Falcon-40B: —, Gemini 3.7 Flash: 78.0 (#12)

Instruction Following benchmarks
BenchmarkFalcon-40BGemini 3.7 Flash
LMArena Instruction Following—1486

Long Context Not comparable

Falcon-40B: —, Gemini 3.7 Flash: 45.8 (#28)

Long Context benchmarks
BenchmarkFalcon-40BGemini 3.7 Flash
LMArena Longer Query—1493

Writing & Preference Not comparable

Falcon-40B: —, Gemini 3.7 Flash: 71.4 (#19)

Writing & Preference benchmarks
BenchmarkFalcon-40BGemini 3.7 Flash
LMArena Text—1487
LMArena Creative Writing—1490
EQ-Bench Creative Writing—1723
LMArena Multi-Turn—1495

Frequently asked questions

Is Falcon-40B better than Gemini 3.7 Flash?

Gemini 3.7 Flash has enough public results to be ranked (#11); Falcon-40B does not yet, so treat this comparison as directional.

How many benchmarks do Falcon-40B and Gemini 3.7 Flash share?

1 benchmark has published results for both models. Falcon-40B has 12 scored results on Noometry and Gemini 3.7 Flash has 44.

Related comparisons

Go deeper