Timeline history

Frontier Model Capabilities and Benchmarks timeline history

Review how this topic changed over time through source-backed timeline events.

Timeline history

All tracked timeline events

200 total timeline events

Jul 12, 2026, 8:41 PM
source update
tychozzz:2076317623739097583
Frontier Model Capabilities and Benchmarks showed a tracked change with evidence attached, making the topic easier to monitor over time.
ContributionAdds evidence to the topic's change timeline.
ImpactThis update may affect teams tracking frontier_model_capabilities_and_benchmarks.
Jul 12, 2026, 8:36 PM
source update
rasbt:2075963073802731782
X post: User: @rasbt Post ID: 2075963073802731782 Text: @RebeccaBra42263 Probably depends on the benchmark composition. This one measures Composite average pass@1 across DeepSWE, T
Contributionchange point: X post: User: @rasbt Post ID: 2075963073802731782 Text: @RebeccaBra42263 Probably depends on the benchmark composition. This one measures Composite average pass@1 across DeepSWE, T
ImpactThis update may affect teams tracking frontier_model_capabilities_and_benchmarks.
Jul 12, 2026, 2:35 AM
source update
petergyang:2076050876314300478
X post: User: @petergyang Post ID: 2076050876314300478 Text: This is super cool but I wonder how all these benchmarks work? How do you benchmark design taste? Metrics: {like_count=
Contributionchange point: X post: User: @petergyang Post ID: 2076050876314300478 Text: This is super cool but I wonder how all these benchmarks work? How do you benchmark design taste? Metrics: {like_count=
ImpactThis update may affect teams tracking frontier_model_capabilities_and_benchmarks.
Jul 11, 2026, 8:40 PM
source update
altryne:2075993750375895546
X post: User: @altryne Post ID: 2075993750375895546 Text: We moved from 3 frontier AI labs to 5 in a single week! This week was the craziest week in AI news, almost since we've do
Contributionchange point: X post: User: @altryne Post ID: 2075993750375895546 Text: We moved from 3 frontier AI labs to 5 in a single week! This week was the craziest week in AI news, almost since we've do
ImpactThis update may affect teams tracking frontier_model_capabilities_and_benchmarks.
Jul 11, 2026, 8:45 AM
source update
emollick:2075597090923696503
X post: User: @emollick Post ID: 2075597090923696503 Text: You can no longer just drop in the smartest model into a harness and expect it to behave similarly to any other model of
Contributionchange point: X post: User: @emollick Post ID: 2075597090923696503 Text: You can no longer just drop in the smartest model into a harness and expect it to behave similarly to any other model of
ImpactThis update may affect teams tracking frontier_model_capabilities_and_benchmarks.
Jul 11, 2026, 8:35 AM
source update
ToolhouseAI:2075631002785808533
X post: User: @ToolhouseAI Post ID: 2075631002785808533 Text: AI Twitter is obsessed with coding-agent benchmarks, model routing, and eval pipelines. Most businesses are asking sim
Contributionchange point: X post: User: @ToolhouseAI Post ID: 2075631002785808533 Text: AI Twitter is obsessed with coding-agent benchmarks, model routing, and eval pipelines. Most businesses are asking sim
ImpactThis update may affect teams tracking frontier_model_capabilities_and_benchmarks.
Jul 11, 2026, 2:35 AM
source update
AravSrinivas:2075661385858732149
X post: User: @AravSrinivas Post ID: 2075661385858732149 Text: Very impressed with @SpaceXAI's Grok 4.5 model. Inside the Computer harness, it scored the highest on our internal be
Contributionchange point: X post: User: @AravSrinivas Post ID: 2075661385858732149 Text: Very impressed with @SpaceXAI's Grok 4.5 model. Inside the Computer harness, it scored the highest on our internal be
ImpactThis update may affect teams tracking frontier_model_capabilities_and_benchmarks.
Jul 10, 2026, 2:40 AM
source update
teslaownersSV:2075372383251374310
X post: User: @teslaownersSV Post ID: 2075372383251374310 Text: GROK 4.5 TAKES #1 AMONG NON-ANTHROPIC MODELS ON NEW AGENTIC BENCHMARK According to Artificial Analysis, Grok 4.5 ran
Contributionchange point: X post: User: @teslaownersSV Post ID: 2075372383251374310 Text: GROK 4.5 TAKES #1 AMONG NON-ANTHROPIC MODELS ON NEW AGENTIC BENCHMARK According to Artificial Analysis, Grok 4.5 ran
ImpactThis update may affect teams tracking frontier_model_capabilities_and_benchmarks.
Jul 9, 2026, 8:30 PM
source update
swyx:2074919183947808881
X post: User: @swyx Post ID: 2074919183947808881 Text: most agent labs are shy about acknowledging chinese model use because they need to sell to gov/defense cog team did the hard
Contributionchange point: X post: User: @swyx Post ID: 2074919183947808881 Text: most agent labs are shy about acknowledging chinese model use because they need to sell to gov/defense cog team did the hard
ImpactThis update may affect teams tracking frontier_model_capabilities_and_benchmarks.
Jul 9, 2026, 8:40 AM
source update
altryne:2075000993394343963
X post: User: @altryne Post ID: 2075000993394343963 Text: OK Round 2: @OpenAI GPT-Live announcement (the full-duplex voice model cc @juberti and gang 👏) Same order every round —
Contributionchange point: X post: User: @altryne Post ID: 2075000993394343963 Text: OK Round 2: @OpenAI GPT-Live announcement (the full-duplex voice model cc @juberti and gang 👏) Same order every round —
ImpactThis update may affect teams tracking frontier_model_capabilities_and_benchmarks.
Jul 8, 2026, 8:50 PM
source update
ArtificialAnlys:2074942097158021371
X post: User: @ArtificialAnlys Post ID: 2074942097158021371 Text: SpaceXAI just released Grok 4.5, and it ranks #4 on GDPval-AA v2 with an Elo of 1543 - behind only the latest Clau
Contributionchange point: X post: User: @ArtificialAnlys Post ID: 2074942097158021371 Text: SpaceXAI just released Grok 4.5, and it ranks #4 on GDPval-AA v2 with an Elo of 1543 - behind only the latest Clau
ImpactThis update may affect teams tracking frontier_model_capabilities_and_benchmarks.
Jul 8, 2026, 8:45 PM
source update
merge_api:2074949525010047317
X post: User: @merge_api Post ID: 2074949525010047317 Text: Grok 4.5 is now live on Merge Gateway. @spacexai + @cursor_ai's new coding and agentic model: 83.3% on Terminal Bench 2
Contributionchange point: X post: User: @merge_api Post ID: 2074949525010047317 Text: Grok 4.5 is now live on Merge Gateway. @spacexai + @cursor_ai's new coding and agentic model: 83.3% on Terminal Bench 2
ImpactThis update may affect teams tracking frontier_model_capabilities_and_benchmarks.
Jul 8, 2026, 8:35 PM
source update
emollick:2074595359364411651
X post: User: @emollick Post ID: 2074595359364411651 Text: MAI-1 has no independent benchmarks yet, but the ones they released suggest it is worse than Sonnet 4.6. Not sure it is
Contributionchange point: X post: User: @emollick Post ID: 2074595359364411651 Text: MAI-1 has no independent benchmarks yet, but the ones they released suggest it is worse than Sonnet 4.6. Not sure it is
ImpactThis update may affect teams tracking frontier_model_capabilities_and_benchmarks.
Jul 7, 2026, 2:25 PM
source update
OfficialLoganK:2073780601006752038
X post: User: @OfficialLoganK Post ID: 2073780601006752038 Text: @edandersen Ammaar is a builder, that’s means (like the rest of our team) he tries all the models constantly. gee
Contributionchange point: X post: User: @OfficialLoganK Post ID: 2073780601006752038 Text: @edandersen Ammaar is a builder, that’s means (like the rest of our team) he tries all the models constantly. gee
ImpactThis update may affect teams tracking frontier_model_capabilities_and_benchmarks.
Jul 7, 2026, 8:45 AM
source update
kimmonismus:2074123763906658562
X post: User: @kimmonismus Post ID: 2074123763906658562 Text: Frontier labs have shifted into rolling-release mode since mid last year. In 2023 and 2024, flagship launches still f
Contributionchange point: X post: User: @kimmonismus Post ID: 2074123763906658562 Text: Frontier labs have shifted into rolling-release mode since mid last year. In 2023 and 2024, flagship launches still f
ImpactThis update may affect teams tracking frontier_model_capabilities_and_benchmarks.
Jul 7, 2026, 8:40 AM
source update
murtuza_merc:2073880890669735983
X post: User: @murtuza_merc Post ID: 2073880890669735983 Text: Nous Research launching Hermes MoA 2.0 proves that brute-forcing massive individual model training runs is hitting a
Contributionchange point: X post: User: @murtuza_merc Post ID: 2073880890669735983 Text: Nous Research launching Hermes MoA 2.0 proves that brute-forcing massive individual model training runs is hitting a
ImpactThis update may affect teams tracking frontier_model_capabilities_and_benchmarks.
Jul 7, 2026, 8:35 AM
source update
ilex_ulmus:2073844158188675558
X post: User: @ilex_ulmus Post ID: 2073844158188675558 Text: Why??? > Fable’s back. Back again. Fable’s back. Tell a friend. Use your free week to its fullest. > This is excellent
Contributionchange point: X post: User: @ilex_ulmus Post ID: 2073844158188675558 Text: Why??? > Fable’s back. Back again. Fable’s back. Tell a friend. Use your free week to its fullest. > This is excellent
ImpactThis update may affect teams tracking frontier_model_capabilities_and_benchmarks.
Jul 7, 2026, 8:35 AM
source update
huajian_xin:2074021303846322433
X post: User: @huajian_xin Post ID: 2074021303846322433 Text: Our Seed Prover team is presenting APE-Bench as a poster at ICML — Jul 9, 1:30–3:15 PM, Hall A #2210. Come by and chat
Contributionchange point: X post: User: @huajian_xin Post ID: 2074021303846322433 Text: Our Seed Prover team is presenting APE-Bench as a poster at ICML — Jul 9, 1:30–3:15 PM, Hall A #2210. Come by and chat
ImpactThis update may affect teams tracking frontier_model_capabilities_and_benchmarks.
Jul 7, 2026, 8:30 AM
source update
LuminaXspace:2074184998937329921
X post: User: @LuminaXspace Post ID: 2074184998937329921 Text: 🚨 New Meta Llama 5 leak just surfaced: Meta appears to be prepping its next massive frontier model to take on OpenA
Contributionchange point: X post: User: @LuminaXspace Post ID: 2074184998937329921 Text: 🚨 New Meta Llama 5 leak just surfaced: Meta appears to be prepping its next massive frontier model to take on OpenA
ImpactThis update may affect teams tracking frontier_model_capabilities_and_benchmarks.
Jul 6, 2026, 2:30 AM
source update
hanakoxbt:2073795018465087903
X post: User: @hanakoxbt Post ID: 2073795018465087903 Text: Anthropic engineer: "Fable 5 does in an hour what Opus 4.6 did overnight, at 40% less cost." In 31 minutes he benchmar
Contributionchange point: X post: User: @hanakoxbt Post ID: 2073795018465087903 Text: Anthropic engineer: "Fable 5 does in an hour what Opus 4.6 did overnight, at 40% less cost." In 31 minutes he benchmar
ImpactThis update may affect teams tracking frontier_model_capabilities_and_benchmarks.