Noometry

Model comparison

Claude 3.5 Haiku vs Falcon-40B

Claude 3.5 Haiku has enough public results to be ranked (#309); Falcon-40B does not yet, so treat this comparison as directional.

Last verified . 2 shared benchmarks.

Claude 3.5 Haiku Anthropic

28.9

Rank #309 Confirmed

Falcon-40B Technology Innovation Institute

—

Unranked

Summary

  • They share 2 benchmarks with published results for both.
  • Falcon-40B has downloadable open weights; the other is API-only.

Side by side

Claude 3.5 HaikuFalcon-40B
ProviderAnthropicTechnology Innovation Institute
Noometry Index28.9—
Released2024-10-222023-03-15
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4912

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

Category by category

Coding Not comparable

Claude 3.5 Haiku: 32.6 (#258), Falcon-40B: —

BenchmarkClaude 3.5 HaikuFalcon-40B
Aider Polyglot28%—
SciCode27.4%—
WeirdML30.7%—
BigCodeBench Instruct46.1%—
LiveBench Coding51.4%—
LMArena Coding1287—
BigCodeBench Complete59%—
CadEval32%—

Agentic & Tool Use Not comparable

Claude 3.5 Haiku: 27.7 (#90), Falcon-40B: —

BenchmarkClaude 3.5 HaikuFalcon-40B
BALROG19.3%—

Reasoning Not comparable

Claude 3.5 Haiku: 17.1 (#286), Falcon-40B: —

BenchmarkClaude 3.5 HaikuFalcon-40B
Epoch Capabilities Index127.15104.04
CritPt0%—
LiveBench Reasoning28.1%—
LMArena Hard Prompts1251—
DTBench56.7%—
LiveBench Data Analysis48.5%—
BIG-Bench Hard—37.1%
HellaSwag—85.3%
LAMBADA—77.3%
LiveBench43.5%—
PIQA—83%
WinoGrande—76.9%

Math Not comparable

Claude 3.5 Haiku: 13.7 (#294), Falcon-40B: —

BenchmarkClaude 3.5 HaikuFalcon-40B
OTIS Mock AIME 2024-20254.3%—
Omni-MATH22.4%—
LiveBench Math35.5%—
LMArena Math1244—
MATH Level 546.4%—
FrontierMath (Feb 2025 set)0.3%—
GSM8K—33.8%

Knowledge Not comparable

Claude 3.5 Haiku: 18.7 (#276), Falcon-40B: —

BenchmarkClaude 3.5 HaikuFalcon-40B
MMLU74.3%56.9%
GPQA Diamond38.1%—
MMLU-Pro60.5%—
Confabulations36.7%—
GPQA (HELM)36.3%—
LMArena Expert1208—
ARC (AI2) Challenge—61.9%
BoolQ—83.1%
OpenBookQA—56.6%
TriviaQA—79.9%

Multimodal Not comparable

Claude 3.5 Haiku: 26.3 (#113), Falcon-40B: —

BenchmarkClaude 3.5 HaikuFalcon-40B
LMArena Vision1092—
GeoBench34%—

Multilingual Not comparable

Claude 3.5 Haiku: 40.2 (#213), Falcon-40B: —

BenchmarkClaude 3.5 HaikuFalcon-40B
LMArena Non-English1238—
LMArena Chinese1229—
LMArena French1262—
LMArena German1237—
LMArena Japanese1175—
LMArena Korean1172—
LMArena Russian1253—
LMArena Spanish1261—

Instruction Following Not comparable

Claude 3.5 Haiku: 63.1 (#229), Falcon-40B: —

BenchmarkClaude 3.5 HaikuFalcon-40B
LiveBench Instruction Following61.9%—
IFEval79.2%—
LMArena Instruction Following1241—

Long Context Not comparable

Claude 3.5 Haiku: 38.3 (#195), Falcon-40B: —

BenchmarkClaude 3.5 HaikuFalcon-40B
LMArena Longer Query1261—

Writing & Preference Not comparable

Claude 3.5 Haiku: 42.9 (#228), Falcon-40B: —

BenchmarkClaude 3.5 HaikuFalcon-40B
LMArena Text1255—
LMArena Creative Writing1233—
Short-Story Creative Writing73.5%—
EQ-Bench Creative Writing1146—
WildBench76%—
LMArena Multi-Turn1265—
LiveBench Language35.4%—

Frequently asked questions

Is Claude 3.5 Haiku better than Falcon-40B?

Claude 3.5 Haiku has enough public results to be ranked (#309); Falcon-40B does not yet, so treat this comparison as directional.

How many benchmarks do Claude 3.5 Haiku and Falcon-40B share?

2 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Falcon-40B has 12.

Related comparisons

Go deeper