Urambazaji
AI BENCHY
Your ad here

AI BENCHY Compare

Modeli zilizolinganishwa

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-03-12

Kipimo Claude Opus 4.6 Claude Opus 4.6 medium Toleo: 2026-02-05 Claude Sonnet 4.6 Claude Sonnet 4.6 medium Toleo: 2026-02-17 GPT-5.3-Codex GPT-5.3-Codex medium Toleo: 2026-02-05 Gemini 3.1 Pro Preview Gemini 3.1 Pro Preview medium Toleo: 2026-02-19
Nafasi #28 #12 #4 #2
Wastani wa alama 6.6 7.7 8.4 9.4
Uthabiti 9.0 9.5 9.1 10.0
Gharama kwa matokeo 13.118 8.525 4.485 3.417
Jumla ya gharama $1.312 $1.023 $0.539 $0.513
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 66.7% 77.1% 83.3% 93.8%
Majaribio yasiyo thabiti 2 1 2 0
Jumla ya uendeshaji 48 48 48 48
Tokeni za matokeo 26,254 35,159 1,764 1,521
Tokeni za hoja 17,363 24,687 33,348 35,656
Muda wa majibu (wastani) 22.86s 11.23s 16.59s 16.60s
Muda wa majibu (upeo) 83.40s 46.35s 100.93s 40.61s
Muda wa majibu (jumla) 205.71s 89.84s 265.39s 149.36s

Modeli bora kwa alama

Alama dhidi ya gharama ya jumla

Muda wa majibu (wastani)

Wastani wa alama vs Muda wa majibu (wastani)

Jumla ya tokeni za matokeo

Wastani wa alama vs Jumla ya tokeni za matokeo

Mgawanyo wa kategoria

Mbinu za kupinga AI Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
Claude Opus 4.6 4.0 4.4 55.6% 2 11.88s 897 1,000
Claude Sonnet 4.6 7.0 10.0 66.7% 0 4.95s 1,031 1,093
GPT-5.3-Codex 10.0 10.0 100.0% 0 4.69s 216 1,421
Gemini 3.1 Pro Preview 10.0 10.0 100.0% 0 9.52s 106 2,533
Mchanganyiko Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
Claude Opus 4.6 10.0 10.0 100.0% 0 76.66s 8,178 5,194
Claude Sonnet 4.6 10.0 10.0 100.0% 0 46.35s 5,871 3,962
GPT-5.3-Codex 10.0 10.0 100.0% 0 19.56s 364 2,731
Gemini 3.1 Pro Preview 9.0 10.0 100.0% 0 40.61s 432 9,281
Uchanganuzi na uchimbaji wa data Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
Claude Opus 4.6 9.9 10.0 100.0% 0 7.37s 691 757
Claude Sonnet 4.6 9.9 10.0 100.0% 0 13.90s 649 742
GPT-5.3-Codex 9.9 10.0 100.0% 0 3.07s 234 728
Gemini 3.1 Pro Preview 9.9 10.0 100.0% 0 7.72s 279 3,904
Mahususi kwa domeni Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
Claude Opus 4.6 10.0 10.0 0.0% 0 83.40s 14,642 8,687
Claude Sonnet 4.6 10.0 7.2 11.1% 1 0ms 25,790 16,919
GPT-5.3-Codex 4.0 7.2 55.6% 1 64.31s 64 25,308
Gemini 3.1 Pro Preview 7.0 10.0 66.7% 0 32.73s 18 12,424
Akili ya jumla Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
Claude Opus 4.6 10.0 10.0 100.0% 0 5.04s 188 292
Claude Sonnet 4.6 10.0 10.0 100.0% 0 4.94s 256 433
GPT-5.3-Codex 4.0 10.0 0.0% 0 4.87s 187 331
Gemini 3.1 Pro Preview 10.0 10.0 100.0% 0 11.77s 108 1,179
Ufuataji wa maagizo Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
Claude Opus 4.6 10.0 10.0 100.0% 0 2.43s 266 467
Claude Sonnet 4.6 10.0 10.0 100.0% 0 2.61s 318 552
GPT-5.3-Codex 10.0 10.0 100.0% 0 3.04s 93 693
Gemini 3.1 Pro Preview 10.0 10.0 100.0% 0 9.56s 72 2,236
Puzzle Solving Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
Claude Opus 4.6 7.0 10.0 66.7% 0 4.60s 531 637
Claude Sonnet 4.6 10.0 10.0 100.0% 0 4.80s 589 635
GPT-5.3-Codex 9.3 7.9 88.9% 1 5.12s 352 1,644
Gemini 3.1 Pro Preview 10.0 10.0 100.0% 0 7.15s 232 3,117
Mwito wa zana Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
Claude Opus 4.6 10.0 10.0 100.0% 0 9.73s 861 329
Claude Sonnet 4.6 10.0 10.0 100.0% 0 7.48s 655 351
GPT-5.3-Codex 10.0 10.0 100.0% 0 6.37s 254 492
Gemini 3.1 Pro Preview 10.0 10.0 100.0% 0 23.15s 274 982

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho