Score history · Kimi K2.7 Code 3 rows

Not enough history to chart — 3 observations, all dated 11 Sept 2026. Rows under different configurations count separately; the list below shows each one.

44.7%aa_slug=kimi-k2-7-code · variant=hard · evaluator=Artificial Analysis · index_version=4.311 Sept 2026
67.42%aa_slug=kimi-k2-7-code · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.311 Sept 2026
1.01%aa_slug=kimi-k2-7-code · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.311 Sept 2026

Back to the full leaderboard

Leaderboard 821 current results

Select models with +, then open Compare.

Leaderboard
#	Model	Score	Config	Evaluated	Source	Actions
801	#801Qwen3 235B A22B Instruct 2507Qwen	0%	aa_slug=qwen3-235b-a22b-instruct-2507-reasoning · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3	— (obs. 11 Sept 2026)	artificialanalysis.aiT2	History
802	#802exaone-4-0-1-2bLG AI Research	0%	aa_slug=exaone-4-0-1-2b · variant=hard · evaluator=Artificial Analysis · index_version=4.3	— (obs. 11 Sept 2026)	artificialanalysis.aiT2	History
803	#803DeepSeek V3 0324DeepSeek	0%	aa_slug=deepseek-v3-0324 · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3	— (obs. 11 Sept 2026)	artificialanalysis.aiT2	History
804	#804jamba-1-7-miniAI21 Labs	0%	aa_slug=jamba-1-7-mini · variant=hard · evaluator=Artificial Analysis · index_version=4.3	— (obs. 11 Sept 2026)	artificialanalysis.aiT2	History
805	#805nvidia-nemotron-3-nano-30b-a3b-reasoningNVIDIA	0%	aa_slug=nvidia-nemotron-3-nano-30b-a3b-reasoning · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3	— (obs. 11 Sept 2026)	artificialanalysis.aiT2	History
806	#806minicpm5-1bOpenBMB	0%	aa_slug=minicpm5-1b · variant=hard · evaluator=Artificial Analysis · index_version=4.3	— (obs. 11 Sept 2026)	artificialanalysis.aiT2	History
807	#807olmo-2-7bAllen Institute for AI	0%	aa_slug=olmo-2-7b · variant=hard · evaluator=Artificial Analysis · index_version=4.3	— (obs. 11 Sept 2026)	artificialanalysis.aiT2	History
808	#808Mercury 2Inception	0%	aa_slug=mercury-2 · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3	— (obs. 11 Sept 2026)	artificialanalysis.aiT2	History
809	#809Solar Pro 3Upstage	0%	aa_slug=solar-pro-3 · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3	— (obs. 11 Sept 2026)	artificialanalysis.aiT2	History
810	#810gpt-5-miniOpenAI	0%	aa_slug=gpt-5-mini · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3	— (obs. 11 Sept 2026)	artificialanalysis.aiT2	History
811	#811minicpm-v4-6-1-3bOpenBMB	0%	aa_slug=minicpm-v4-6-1-3b · variant=hard · evaluator=Artificial Analysis · index_version=4.3	— (obs. 11 Sept 2026)	artificialanalysis.aiT2	History
812	#812Qwen3.5-122B-A10BQwen	0%	aa_slug=qwen3-5-122b-a10b · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3	— (obs. 11 Sept 2026)	artificialanalysis.aiT2	History
813	#813minicpm-v4-6-1-3bOpenBMB	0%	aa_slug=minicpm-v4-6-1-3b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3	— (obs. 11 Sept 2026)	artificialanalysis.aiT2	History
814	#814celeris-1Celeris	0%	aa_slug=celeris-1 · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3	— (obs. 11 Sept 2026)	artificialanalysis.aiT2	History
815	#815Ling 3.0 Flash VLinclusionAI	0%	aa_slug=ling-3-0-flash-vl · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3	— (obs. 11 Sept 2026)	artificialanalysis.aiT2	History
816	#816Gemma 4 31BGoogle	0%	aa_slug=gemma-4-31b · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3	— (obs. 11 Sept 2026)	artificialanalysis.aiT2	History
817	#817deepseek-v3DeepSeek	0%	aa_slug=deepseek-v3 · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3	— (obs. 11 Sept 2026)	artificialanalysis.aiT2	History
818	#818Mistral Small 3.2Mistral AI	0%	aa_slug=mistral-small-3-2 · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3	— (obs. 11 Sept 2026)	artificialanalysis.aiT2	History
819	#819Qwen3 14BQwen	0%	aa_slug=qwen3-14b-instruct-reasoning · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3	— (obs. 11 Sept 2026)	artificialanalysis.aiT2	History
820	#820LFM2.5-1.2B-InstructLiquid AI	0%	aa_slug=lfm2-5-1-2b-instruct · variant=hard · evaluator=Artificial Analysis · index_version=4.3	— (obs. 11 Sept 2026)	artificialanalysis.aiT2	History
821	#821Devstral Small 2Mistral AI	0%	aa_slug=devstral-small-2 · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3	— (obs. 11 Sept 2026)	artificialanalysis.aiT2	History

Scores are reported as published, with their evaluation configuration (harness, prompting, judge). The bar is relative to the best score on this page. Results with different configs are not directly comparable — see methodology.

The config filter matches a value inside each result's configuration (server-side, `config=` on the API). Chips are the values shared by several rows on the first page; per-model identifiers are not offered.

Definition

Category: agentic
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 9 h agomedium
Task: terminal tasks solved by agents
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 9 h agomedium
Metric: accuracy · %
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 9 h agomedium
Direction: Higher is better
Website: tbench.ai
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 9 h agomedium

Each value shows its source, tier and observation time. Missing rows mean no source stated them. How results are recorded →

Evaluated models: grok-3-mini-reasoning, claude-opus-5-medium, gemma-4-12B, deepseek-v4-flash, grok-4-3-low, GPT-5.1-Codex Mini, Qwen3 Coder Next, KAT-Coder-Pro V2 +523(531 total)

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history

5 claims · 5 properties

Categorycategory1

Claim history for Category
Value	Valid from → to	Status	Source	Confidence	Extractor
agentic	11 Sept 2026 20:50 UTC → current	current	AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2	medium	curated

Metricmetric1

Claim history for Metric
Value	Valid from → to	Status	Source	Confidence	Extractor
accuracy	11 Sept 2026 20:50 UTC → current	current	AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2	medium	curated

Tasktask1

Claim history for Task
Value	Valid from → to	Status	Source	Confidence	Extractor
terminal tasks solved by agents	11 Sept 2026 20:50 UTC → current	current	AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2	medium	curated

Unitunit1

Claim history for Unit
Value	Valid from → to	Status	Source	Confidence	Extractor
%	11 Sept 2026 20:50 UTC → current	current	AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2	medium	curated

Websitewebsite1

Claim history for Website
Value	Valid from → to	Status	Source	Confidence	Extractor
https://www.tbench.ai	11 Sept 2026 20:50 UTC → current	current	AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2	medium	curated

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

11 Sept 2026
New benchmarkBenchmarkTerminal-Bench
New benchmark: Terminal-Bench
registry
tbench.ai

Full timeline →

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
Artificial Analysis	artificialanalysis.ai/leaderboards/models	leaderboard	T2· Quality secondary	8 h ago	1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.