instruction decay 相关资讯

原创

WDCD Run #331: Grok 4 Leads at 91.8 as Average Instruction Decay Hits -15.1%

WDCD Run #331 (2026-09-20) evaluated 11 models on multi-turn commitment integrity, with Grok 4 topping the ranking at 91

WDCD AI benchmark instruction decay multi-turn

2天前 194

原创

WDCD Run #326: DeepSeek V4 Pro and Gemini 3.1 Pro Achieve Perfect Decay Resistance as Fleet Average Drops 72.7%

WDCD Run #326 (2026-09-16) tested 11 models on multi-turn commitment integrity, recording an average commitment decay of

WDCD AI benchmark instruction decay multi-turn

6天前 198

原创

WDCD Run #316: Grok 4 Leads Multi-Turn Commitment Benchmark as Claude Sonnet 4.6 Sets Decay Resistance Record

WDCD Run #316 (2026-09-09) benchmarked 11 frontier models on multi-turn instruction adherence, with Grok 4 taking the to

WDCD AI benchmark instruction decay multi-turn

2026年9月9日 340

原创

WDCD Run #311: Grok 4 Leads with 93.2 Points as GLM-4.6 Sets New Decay Resistance Record

WDCD Run #311 (2026-09-06) evaluated 11 models across three-round multi-turn dialogues, with Grok 4 taking the top score

WDCD AI benchmark instruction decay multi-turn

2026年9月6日 333

原创

WDCD Run #306: Average Instruction Decay Hits -45.5% as Gemini 3.1 Pro Leads at 97.7 Points

WDCD Run #306 (2026-09-02) evaluated 11 models across three dialogue rounds, recording an average commitment decay of -4

WDCD AI benchmark instruction decay multi-turn

2026年9月2日 435

原创

WDCD Run #296: Zero Instruction Decay Across All 11 Models, Grok 4 Leads at 96.3

WDCD Run #296 (2026-08-26) recorded 0% average commitment decay across 11 tested models, with Grok 4 topping the ranking

WDCD AI benchmark instruction decay multi-turn

2026年8月26日 408

原创

WDCD Run #291: Grok 4 Leads with 94 Points as Average Multi-Turn Instruction Decay Hits -7.2%

WDCD Run #291 (2026-08-23) evaluated 11 models across three dialogue rounds, recording an average commitment decay of -7

WDCD AI benchmark instruction decay multi-turn

2026年8月23日 389

原创

WDCD Run #285: Average Instruction Decay Hits 54.5% Across 11 Models, Grok 4 Leads with Zero Drift

WDCD Run #285 (2026-08-19) tested 11 frontier models across three dialogue rounds and recorded an average commitment dec

WDCD AI benchmark instruction decay multi-turn

2026年8月19日 349

原创

WDCD Run #276: Grok 4 Leads with 94.8 Points as Average Instruction Decay Hits -18.2%

WDCD Run #276 (2026-08-12) evaluated 11 models on multi-turn commitment integrity, with Grok 4 taking the top spot at 94

WDCD AI benchmark instruction decay multi-turn

2026年8月12日 347

原创

WDCD Run #271: Grok 4 Leads as Average Instruction Decay Drops to 0.9%

WDCD Run #271 (2026-08-09) tested 11 models across three rounds of multi-turn commitment scoring, recording an average i

WDCD AI benchmark instruction decay multi-turn

2026年8月9日 273

原创

WDCD Run #263: Grok 4 Leads With 97.5 Points as Average Instruction Decay Hits -18.2%

WDCD Run #263 (2026-08-05) evaluated 11 models across three dialogue rounds, recording an average commitment decay of -1

WDCD AI benchmark instruction decay multi-turn

2026年8月5日 897

原创

WDCD Run #253: Grok 4 Leads with 94.8 Points as Average Instruction Decay Holds at 4.5%

WDCD Run #253 (2026-07-29) tested 11 models across three dialogue rounds, recording an average commitment decay of 4.5%.

WDCD AI benchmark instruction decay multi-turn

2026年7月29日 656

原创

WDCD Run #247: Grok 4 Leads with Negative Decay as Average Instruction Decay Narrows to -1.8%

WDCD Run #247 (2026-07-26) evaluated 11 models across three dialogue rounds, recording an average commitment decay of -1

WDCD AI benchmark instruction decay multi-turn

2026年7月26日 525

原创

WDCD Run #242: Grok 4 and GLM-4.6 Hold Zero Instruction Decay as Gemini 3.1 Pro Collapses at -100%

WDCD Run #242 (2026-07-22) evaluated 11 models across three-round multi-turn dialogues, recording an average commitment

WDCD AI benchmark instruction decay multi-turn

2026年7月22日 686

原创

WDCD Run #233: GPT-o3 Leads with Zero Instruction Decay, Gemini 3.1 Pro Collapses Completely

WDCD Run #233 (2026-07-15) evaluated 11 frontier models on multi-turn commitment integrity, recording an average instruc

WDCD AI benchmark instruction decay multi-turn

2026年7月15日 513

原创

WDCD Run #227: Grok 4 and DeepSeek V4 Pro Tie at 91.4 as Instruction Decay Averages -2.8% Across 11 Models

WDCD Run #227 (2026-07-12) evaluated 11 frontier models on multi-turn commitment integrity, with Grok 4 and DeepSeek V4

WDCD AI benchmark instruction decay multi-turn

2026年7月12日 1,264

原创

WDCD Run #221: Average Instruction Decay Hits -36.4% as Grok 4 Leads 11-Model Field

WDCD Run #221 (2026-07-08) measured instruction decay across 11 frontier models over three dialogue rounds, recording an

WDCD AI benchmark instruction decay multi-turn

2026年7月8日 506

原创

WDCD Run #211: Grok 4 Leads with Just -13% Instruction Decay as GPT-o3 Collapses at -75%

WDCD Run #211 (2026-07-03) benchmarked 11 models on multi-turn commitment integrity, with Grok 4 taking the top spot at

WDCD AI benchmark instruction decay multi-turn

2026年7月3日 514

原创

WDCD Run #207: Average Instruction Decay Hits -66.3% Across 11 Models, Grok 4 Leads Field

WDCD Run #207 (2026-07-01) measured multi-turn commitment across 11 frontier models, recording an average commitment dec

WDCD AI benchmark instruction decay multi-turn

2026年7月1日 504

原创

WDCD Run #202: Average Instruction Decay Hits -73.2% Across 11 Models, Gemini 3.1 Pro Leads

WDCD Run #202 (2026-06-28) measured multi-turn commitment integrity across 11 frontier models, recording an average inst

WDCD AI benchmark instruction decay multi-turn

2026年6月28日 597