What changed between 5 Sept 2026 and 12 Sept 2026
Two dates, one scope: new and retired models, price and context changes, new benchmark leaders, new papers, provider and hardware changes. Built from the change log keyed on when things occurred — nothing is inferred, and the URL is the report.
Scope: organization · LG AI Research
50 events in the window · 0 claims superseded · price rows opened 0 / closed 0 · entities at 5 Sept 2026: 0 → at 12 Sept 2026: 10. Events are keyed on occurred_at (effective date when known) and exclude back-filled history unless include_backfill=1; new_entities uses first_seen_at. new_benchmark_leaders compares the primary-group leader computed from results observed by each date.
New models
New models 5
| Model | Organization | Params | Context | Openness | Released | First seen |
|---|---|---|---|---|---|---|
| k-exaone-2-0-0803 | LG AI Research | — | 262.1K | Open weights | — | 11 Sept 2026 |
| exaone-4-0-32b | LG AI Research | — | 131K | Open weights | — | 11 Sept 2026 |
| exaone-4-5-33b | LG AI Research | — | 262.1K | Open weights | — | 11 Sept 2026 |
| k-exaone | LG AI Research | — | 256K | Open weights | — | 11 Sept 2026 |
| exaone-4-0-1-2b | LG AI Research | — | 64K | Open weights | — | 11 Sept 2026 |
Retired models
Retired models 0
No model was retired between these dates
Price changes
Price changes 0
No price change between these dates
Context changes
Context changes 0
No context-window change between these dates
New benchmark leaders
New benchmark leaders 23
Benchmarks whose primary-group leader (computed from results observed by each date) differs between 5 Sept 2026 and 12 Sept 2026.
| Benchmark | Leader at 5 Sept 2026 | Score | Leader at 12 Sept 2026 | Score | Metric |
|---|---|---|---|---|---|
| Aider polyglotcoding | no result observed yet | — | gpt-5 | 86.7 | pass_rate_2official-benchmark |
| Aider polyglot — well-formed responsescoding | no result observed yet | — | Codestral 25.01 | 100 | percent_cases_well_formedofficial-benchmark |
| Artificial Analysis Intelligence Indexcomposite | no result observed yet | — | Claude Fable 5.1 | 53.37 | indexindependent-evaluator |
| GPQA Diamondreasoning | no result observed yet | — | gpt-6-astra | 96.26 | accuracyindependent-evaluator |
| Humanity's Last Examknowledge | no result observed yet | — | Claude Fable 5.1 | 59.13 | accuracyindependent-evaluator |
| IFBenchinstruction-following | no result observed yet | — | Grok 4.3 | 83.33 | accuracyindependent-evaluator |
| LiveBenchgeneral | no result observed yet | — | Claude Fable 5.1 | 83.41 | global_averageofficial-benchmark |
| LiveBench Agentic Codingcoding | no result observed yet | — | DeepSeek-V4.1-Flash | 77.27 | average scoreofficial-benchmark |
| LiveBench Codingcoding | no result observed yet | — | Claude Fable 5.1 | 86.38 | average scoreofficial-benchmark |
| LiveBench Data Analysisgeneral | no result observed yet | — | gpt-6-astra | 82.97 | average scoreofficial-benchmark |
| LiveBench Instruction Followinginstruction-following | no result observed yet | — | Gemini 3.8 Flash | 81.41 | average scoreofficial-benchmark |
| LiveBench Languagegeneral | no result observed yet | — | Claude Fable 5 | 90.68 | average scoreofficial-benchmark |
| LiveBench Mathematicsmath | no result observed yet | — | Claude Fable 5.1 | 97.01 | average scoreofficial-benchmark |
| LiveBench Reasoningreasoning | no result observed yet | — | gpt-6-astra | 92.65 | average scoreofficial-benchmark |
| MMMU-Promultimodal | no result observed yet | — | gpt-6-astra | 86.88 | accuracyindependent-evaluator |
| SWE-bench (full test split)coding | no result observed yet | — | claude-3-opus | 3.79 | resolvedofficial-benchmark |
| SWE-bench Litecoding | no result observed yet | — | claude-3-opus | 4.33 | resolvedofficial-benchmark |
| SWE-bench Multilingualcoding | no result observed yet | — | gemini-3-flash | 72.7 | resolvedofficial-benchmark |
| SWE-bench Multimodalcoding | no result observed yet | — | o3 | 35.98 | resolvedofficial-benchmark |
| SWE-bench Verifiedcoding | no result observed yet | — | Claude Opus 4.5 | 76.8 | resolvedofficial-benchmark |
| SciCodecoding | no result observed yet | — | Claude Fable 5.1 | 63.08 | accuracyindependent-evaluator |
| Terminal-Benchagentic | no result observed yet | — | gpt-5.6-sol | 65.91 | accuracyindependent-evaluator |
| τ²-benchagentic | no result observed yet | — | Z.ai GLM 5.2 | 99.12 | pass^1independent-evaluator |
New papers
New papers 0
No new paper between these dates
Provider changes
Provider changes 0
No provider listing or delisting between these dates
Hardware changes
Hardware changes 0
No hardware change between these dates
Other property changes
Other property changes 0
Openness, licence, status, parameters, release-date and other material property changes (context changes are listed above).
No other property change between these dates
Other new entities
Other new entities 5
| Entity | Type | Organization | First seen |
|---|---|---|---|
| EXAONE 2.0 | Family | LG AI Research | 11 Sept 2026 |
| EXAONE 4.5 | Family | LG AI Research | 11 Sept 2026 |
| EXAONE | Family | LG AI Research | 11 Sept 2026 |
| EXAONE 4.0 | Family | LG AI Research | 11 Sept 2026 |
| LG AI Research | Lab | — | 11 Sept 2026 |
Gone entities
Gone entities 0
No entity disappeared between these dates
“Gone” means an entity present at the first date is no longer current at the second (merged or retired) — its record and history are kept. Events are keyed on occurred_at; back-filled history is excluded (tick “include backfill” to add it). Per-entity history: any entity's History tab. Atlas as of 5 Sept 2026 · Methodology →