Meta Agents Research Environments (ARE) / Gaia2
Simulated app environments for agents with time and events. Hosts the Gaia2 benchmark.
Gaia2 has 800 dynamic scenarios across 10 universes. In 2026 Meta added Gaia2 CLI, a container stack that runs agents such as OpenClaw and mini-SWE-agent, and the Omnilingual-Gaia2 translation.
- Made by
- Meta FAIR
- Released
- September 2025
- Kind
- General assistants
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Strongest model tested
- GPT-5 #70 on the capability index
- Last in a launch post
- August 2026, dropped before it saturated
- Last model added
- October 2026
- Scores refreshed
- November 12th, 2026
GPT-5 leads with 42.1% among models released by September 2025
Best score per model from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best.
Ring-2.6-1T leads with 77.9%, claims included
Best score per model from every source, including labs’ own numbers and claims Epoch AI collected from reports and papers. Labs pick their own settings, so a claim can beat an independent run of the same model.
The newest model with a score here came out in September 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- Claude Fable 5.2
-
Gemini 4 Carbon - GPT-6 Astra
- Claude Opus 5.5
- and 16 more
- 1 GPT-5 high 42.1%
- 2 Claude Sonnet 4 thinking 37.8%
- 3 Gemini 2.5 Pro Jun 2025 25.8%
- 4
DeepSeek-V3.1-Terminus 23.1% - 5 DeepSeek-V3.1 21.9%
- 6 Kimi K2 Sep 2025 20.1%
- 7 Grok 4 15.7%
- 8
Qwen3-235B-A22B-Thinking Jul 2025, thinking 15.7% - 9 gpt-oss-120b high 13.7%
- 10 Qwen3-235B-A22B 11.6%
- 11 GPT-4o Mar 2025 7.40%
- 12
Llama 4 Maverick 7.40% - 13 Llama 3.3 70B Instruct 4.40%
Source: Official Meta Agents Research Environments (ARE) / Gaia2 leaderboard
- 77.9
Ring-2.6-1T - 75.0 Ring-2.5-1T
- 43.3 Muse Glimmer
- 42.1 GPT-5
- 37.8 Claude Sonnet 4
- 25.8 Gemini 2.5 Pro
- 23.1 DeepSeek-V3.1-Terminus
- 21.9 DeepSeek-V3.1
- 20.1 Kimi K2
- 15.7 Grok 4
- 15.7 Qwen3-235B-A22B-Thinking
- 13.7 gpt-oss-120b
- 11.6 Qwen3-235B-A22B
- 7.40 GPT-4o
- 7.40 Llama 4 Maverick
- 4.40 Llama 3.3 70B Instruct
- 1 Ring-2.6-1T 77.9%
- 2 Ring-2.5-1T 75%
- 3 Muse Glimmer 43.3%
- 4 GPT-5 high 42.1%
- 5 Claude Sonnet 4 thinking 37.8%
- 6 Gemini 2.5 Pro Jun 2025 25.8%
- 7 DeepSeek-V3.1-Terminus 23.1%
- 8 DeepSeek-V3.1 21.9%
- 9 Kimi K2 Sep 2025 20.1%
- 10 Grok 4 15.7%
- 11 Qwen3-235B-A22B-Thinking Jul 2025, thinking 15.7%
- 12 gpt-oss-120b high 13.7%
- 13 Qwen3-235B-A22B 11.6%
- 14 GPT-4o Mar 2025 7.40%
- 15 Llama 4 Maverick 7.40%
- 16 Llama 3.3 70B Instruct 4.40%
Sources: Labs’ model cards and official Meta Agents Research Environments (ARE) / Gaia2 leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5 | 42.1% | high | Aug 2025 | Official leaderboard |
| 2 | Claude Sonnet 4 | 37.8% | thinking | May 2025 | Official leaderboard |
| 3 | Gemini 2.5 Pro Jun 2025 | 25.8% | Jun 2025 | Official leaderboard | |
| 4 | DeepSeek-V3.1-Terminus | 23.1% | Sep 2025 | Official leaderboard | |
| 5 | DeepSeek-V3.1 | 21.9% | Aug 2025 | Official leaderboard | |
| 6 | Kimi K2 Sep 2025 | 20.1% | Sep 2025 | Official leaderboard | |
| 7 | Grok 4 | 15.7% | Jul 2025 | Official leaderboard | |
| 8 | Qwen3-235B-A22B-Thinking Jul 2025 | 15.7% | thinking | Jul 2025 | Official leaderboard |
| 9 | gpt-oss-120b | 13.7% | high | Aug 2025 | Official leaderboard |
| 10 | Qwen3-235B-A22B | 11.6% | Apr 2025 | Official leaderboard | |
| 11 | GPT-4o Mar 2025 | 7.40% | Mar 2025 | Official leaderboard | |
| 12 | Llama 4 Maverick | 7.40% | Apr 2025 | Official leaderboard | |
| 13 | Llama 3.3 70B Instruct | 4.40% | Dec 2024 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Ring-2.6-1T | 77.9% | Jun 2026 | Lab model card | |
| 2 | Ring-2.5-1T | 75% | Feb 2026 | Lab model card | |
| 3 | Muse Glimmer | 43.3% | Aug 2026 | Lab model card | |
| 4 | GPT-5 | 42.1% | high | Aug 2025 | Official leaderboard |
| 5 | Claude Sonnet 4 | 37.8% | thinking | May 2025 | Official leaderboard |
| 6 | Gemini 2.5 Pro Jun 2025 | 25.8% | Jun 2025 | Official leaderboard | |
| 7 | DeepSeek-V3.1-Terminus | 23.1% | Sep 2025 | Official leaderboard | |
| 8 | DeepSeek-V3.1 | 21.9% | Aug 2025 | Official leaderboard | |
| 9 | Kimi K2 Sep 2025 | 20.1% | Sep 2025 | Official leaderboard | |
| 10 | Grok 4 | 15.7% | Jul 2025 | Official leaderboard | |
| 11 | Qwen3-235B-A22B-Thinking Jul 2025 | 15.7% | thinking | Jul 2025 | Official leaderboard |
| 12 | gpt-oss-120b | 13.7% | high | Aug 2025 | Official leaderboard |
| 13 | Qwen3-235B-A22B | 11.6% | Apr 2025 | Official leaderboard | |
| 14 | GPT-4o Mar 2025 | 7.40% | Mar 2025 | Official leaderboard | |
| 15 | Llama 4 Maverick | 7.40% | Apr 2025 | Official leaderboard | |
| 16 | Llama 3.3 70B Instruct | 4.40% | Dec 2024 | Official leaderboard |
Labs report scores for 3 models in their cards. Switch the scores above to rank them together.
Number one over time 3 models have held number one with claims included since its release in September 2025
Lab claims count from the day the card came out, independent runs from the model’s release. We draw one row each for the benchmark’s own leaderboard and what labs claim in their cards.
Sources: Official Meta Agents Research Environments (ARE) / Gaia2 leaderboard and labs’ model cards
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Sources: Official Meta Agents Research Environments (ARE) / Gaia2 leaderboard and labs’ model cards
Labs headline it less often now, last in August 2026
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Aug 10, 2026 | Muse Glimmer | 43.3 | Gaia2 |
| Feb 10, 2026 | Ring-2.5-1T | 75 | Gaia2-search (Mean@3) |
2 system cards report it, from 2 labs
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Oct 19, 2026 | Muse Glimmer technical report | 43.3 | GAIA2, high (Table 2) | Capabilities |
| Jun 13, 2026 | Ring-2.6-1T technical report | 77.9 | GAIA-2 Search (Pass@1, 3 runs), xhigh (Table 6). High gives 75.40 | Capabilities |
More in Tool use
- AutomationBench In use Agent completes end-to-end business workflows inside a simulated company exposing dozens of REST APIs. Graded on resulting state. Gemini 4 Carbon 53.9%
- MCP Atlas In use Multi-step workflows over real MCP servers. Scores tool-use competency on realistic tasks. Gemini 4 Argon 90.7%
- BFCL V4 In use Models call functions and tools, including multi-turn agentic tasks with web search and memory. Checked against expected calls and outcomes. Qwen3.7-Max 75%
- τ³-bench Banking In use Agents act as banking customer-service reps over many turns with a simulated user, following policy. Pass^1 on the final database state. Qwen 3.8 Max 55.1%
- Toolathlon-Verified In use 108 long-horizon tasks across 32 apps through about 600 MCP tools. Execution-based checkers inspect final environment state. GLM-5.3-Flash 78.4%
- DeepSearchQA In use Questions that need multi-step search and synthesis. Final answers graded against references. Kimi K3 95%