BenchmarkActivecategory · agentic
quality57
Updated 7 h ago · first seen 11 Sept 2026
bench_01M293SPFPKK4MF90JEDK0PH8C
- Metric
- accuracy · %
- Direction
- Higher is better
- Results
- 821 · 238 filtered
- Leader
- Claude Fable 5.1 91.39%
Score history · Gemini 3.5 Flash 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.
- 40.91%aa_slug=gemini-3-5-flash · variant=hard · evaluator=Artificial Analysis · index_version=4.311 Sept 2026
- 78.65%aa_slug=gemini-3-5-flash · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.311 Sept 2026
- 6.57%aa_slug=gemini-3-5-flash · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.311 Sept 2026
Leaderboard 238 current results · config contains “v2.1”
Select models with +, then open Compare.
| # | Model | Score | Config | Evaluated | Source | Actions |
|---|---|---|---|---|---|---|
| #201Llama 4 MaverickMeta AI | 7.87% | aa_slug=llama-4-maverick · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #202nvidia-nemotron-3-nano-30b-a3b-reasoningNVIDIA | 6.74% | aa_slug=nvidia-nemotron-3-nano-30b-a3b-reasoning · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #203qwen3-next-80b-a3b-reasoningAlibaba Group | 6.74% | aa_slug=qwen3-next-80b-a3b-reasoning · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #204nemotron-3-nano-omni-30b-a3bNVIDIA | 6.74% | aa_slug=nemotron-3-nano-omni-30b-a3b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #205g9v3-3bAI9Stars | 5.99% | aa_slug=g9v3-3b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #206gpt-4o-miniOpenAI | 5.62% | aa_slug=gpt-4o-mini · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #207Mistral Small 3.2Mistral AI | 5.62% | aa_slug=mistral-small-3-2 · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #208Qwen3 32BQwen | 5.24% | aa_slug=qwen3-32b-instruct-reasoning · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #209Qwen3 14BQwen | 4.87% | aa_slug=qwen3-14b-instruct-reasoning · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #210Llama 3.3 70BMeta AI | 4.87% | aa_slug=llama-3-3-instruct-70b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #211LFM2.5-2.6B (free)Liquid AI | 4.49% | aa_slug=lfm2-5-2-6b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #212o3 Mini HighOpenAI | 4.49% | aa_slug=o3-mini-high · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #213Gemma 3 27BGoogle | 4.49% | aa_slug=gemma-3-27b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #214Magistral Small 1.2Mistral AI | 4.49% | aa_slug=magistral-small-2509 · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #215Ministral 3 8BMistral AI | 4.12% | aa_slug=ministral-3-8b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #216gpt-5-miniOpenAI | 3.75% | aa_slug=gpt-5-mini · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #217Llama 4 ScoutMeta AI | 3.75% | aa_slug=llama-4-scout · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #218gpt-4.1-nanoOpenAI | 3.75% | aa_slug=gpt-4-1-nano · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #219nvidia-nemotron-3-nano-4bNVIDIA | 3.75% | aa_slug=nvidia-nemotron-3-nano-4b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #220granite-4.1-8bIBM | 3.37% | aa_slug=granite-4-1-8b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #221Qwen3.5-2BQwen | 3% | aa_slug=qwen3-5-2b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #222granite-4.1-30bIBM | 2.62% | aa_slug=granite-4-1-30b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #223Qwen3 8BQwen | 2.25% | aa_slug=qwen3-8b-instruct-reasoning · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #224gemma-4-E4BGoogle | 1.87% | aa_slug=gemma-4-e4b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #225Llama 3.1 8BMeta AI | 1.5% | aa_slug=llama-3-1-instruct-8b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #226qwen3-30b-a3b-2507-reasoningAlibaba Group | 1.5% | aa_slug=qwen3-30b-a3b-2507-reasoning · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #227granite-4.1-3bIBM | 1.12% | aa_slug=granite-4-1-3b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #228nanbeige4-1-3bNanbeige | 1.12% | aa_slug=nanbeige4-1-3b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #229gemma-3n-e4bGoogle | 0.75% | aa_slug=gemma-3n-e4b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #230gemma-4-E2BGoogle | 0.37% | aa_slug=gemma-4-e2b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #231Gemma 3 4BGoogle | 0.37% | aa_slug=gemma-3-4b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #232phi-4-miniMicrosoft | 0.37% | aa_slug=phi-4-mini · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #233qwen3-5-0-8b-non-reasoningAlibaba Group | 0.37% | aa_slug=qwen3-5-0-8b-non-reasoning · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #234qwen3-5-2b-non-reasoningAlibaba Group | 0% | aa_slug=qwen3-5-2b-non-reasoning · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #235Qwen3.5-0.8BQwen | 0% | aa_slug=qwen3-5-0-8b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #236minicpm-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 | |
| #237Gemma 3 12BGoogle | 0% | aa_slug=gemma-3-12b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #238Ministral 3 3BMistral AI | 0% | aa_slug=ministral-3-3b · variant=v2.1 · 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 7 h agomedium
- Task
- terminal tasks solved by agents
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 7 h agomedium
- Metric
- accuracy · %
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 7 h agomedium
- Direction
- Higher is better
- Website
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 7 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
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| agentic | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Metricmetric1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| accuracy | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Tasktask1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| terminal tasks solved by agents | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Unitunit1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| % | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Websitewebsite1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| https://www.tbench.ai | → 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 →
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Artificial Analysis | artificialanalysis.ai/leaderboards/models | leaderboard | T2· Quality secondary | 5 h ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.