DataLearner logo

Claude3-Haiku Benchmark Details

Claude3-Haiku currently shows benchmark results led by IF Bench (243 / 282, score 36.10), MMMU (67 / 74, score 50.20), HLE (521 / 565, score 4.10).

Benchmark Results

Claude3-Haiku

Benchmark Results

Thinking
Tool usage

General Knowledge

1 evaluations
Benchmark / mode
Score
Rank/total
HLE
Standard Mode
4.10
521 / 565

Other

1 evaluations
Benchmark / mode
Score
Rank/total
GPQA Diamond
Standard Mode
37.40
437 / 463

Coding and Software Engineer

1 evaluations
Benchmark / mode
Score
Rank/total
LiveCodeBench
Standard Mode
15.40
242 / 251

Writing and Creative Capabilities

1 evaluations
Benchmark / mode
Score
Rank/total
Creative Writing
Standard Mode
714.60
100 / 106

Multimodal Understanding

2 evaluations
Benchmark / mode
Score
Rank/total
MMMU
unknown
50.20
67 / 74
MMMU-Pro
Standard Mode
30.80
227 / 229

Agent Level Benchmark

2 evaluations
Benchmark / mode
Score
Rank/total
τ²-Bench - Telecom
Standard ModeTools
21.10
244 / 264
Terminal Bench Hard
Standard ModeTools
0.80
242 / 244

Instruction Following

1 evaluations
Benchmark / mode
Score
Rank/total
IF Bench
Standard Mode
36.10
243 / 282