FrontierCode 2.0
Created by Cognition, 27 Oct 2026 · Higher is better · Website
Versions
| Version | Released | Status | Models |
|---|---|---|---|
| FrontierCode 1.1 | 7 Jul 2026 | Active | 15 |
| FrontierCode 2.0 | 27 Oct 2026 | Active | 31 |
Settings
| Task set | Scoring | Reported by |
|---|---|---|
| All tasks (132) | Score | |
| All tasks (132) | Pass rate |
Bold: Benchmark default based on Leaderboard and Announcement · Download image
Results
Show
- OpenAI
- Anthropic
- Other labs
- Reported in a later post or card, or on the creator’s leaderboard
- OpenAI
- Anthropic
- Other labs
- Reported in a later post or card, or on the creator’s leaderboard
| Model | Harness and effort | Score | Source |
|---|---|---|---|
| Claude Fable 5.29 Nov 2026 | Claude Codexhigh effort | 49.1% | Introducing Claude Fable 5.2 and Claude Mythos 5.2Corroborated The same number is printed in 2 other documents: 1 2Run by Cognition · mean@5, per the system cardScored before Cognition updated its cheating scanner to remove false positives and rescored all results on 11 Nov 2026 |
| Claude Fable 5.29 Nov 2026 | Claude Codelow effort | 34.2% | Introducing Claude Fable 5.2 and Claude Mythos 5.2Corroborated The same number is printed in 2 other documents: 1 2Run by Cognition · mean@5, per the system card · another reportScored before Cognition updated its cheating scanner to remove false positives and rescored all results on 11 Nov 2026 |
| Claude Fable 5.29 Nov 2026 | Claude Codemedium effort | 37.6% | Introducing Claude Fable 5.2 and Claude Mythos 5.2Corroborated The same number is printed in 2 other documents: 1 2Run by Cognition · mean@5, per the system card · another reportScored before Cognition updated its cheating scanner to remove false positives and rescored all results on 11 Nov 2026 |
| Claude Fable 5.29 Nov 2026 | Claude Codehigh effort | 45.3% | Introducing Claude Fable 5.2 and Claude Mythos 5.2Corroborated The same number is printed in 2 other documents: 1 2Run by Cognition · mean@5, per the system card · another reportScored before Cognition updated its cheating scanner to remove false positives and rescored all results on 11 Nov 2026 |
| Claude Fable 5.29 Nov 2026 | Claude Codemax effort | 45.6% | Introducing Claude Fable 5.2 and Claude Mythos 5.2Corroborated The same number is printed in 1 other document: 1Run by Cognition · mean@5, per the system card · another reportScored before Cognition updated its cheating scanner to remove false positives and rescored all results on 11 Nov 2026 |
| Claude Fable 5.29 Nov 2026 | Claude Codemax effort | 45.7% | Claude Fable 5.2 and Claude Mythos 5.2 System CardChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Run by Cognition · mean@5 · includes the graded scores of 22 attempts (out of 660) that timed out · another reportScored before Cognition updated its cheating scanner to remove false positives and rescored all results on 11 Nov 2026 |
| Claude Fable 5.29 Nov 2026 | Claude Codexhigh effort | 50.2% | FrontierCode LeaderboardChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Cognition’s leaderboard, 18 Nov 2026 · another reportOur capture |
| Gemini 4 Neon18 Nov 2026 | Harness not specifiedhigh thinking | 46.2% | Introducing Gemini 4 NeonCorroborated The same number is printed in 4 other documents. The first 3 are linked: 1 2 3Run by Cognition · set and measure of the official public leaderboard the evaluation methodology citesSource image |
| Gemini 4 Neon18 Nov 2026 | Antigravity CLIhigh effort | 46.2% | FrontierCode LeaderboardCorroborated The same number is printed in 1 other document: 1Cognition’s leaderboard, 18 Nov 2026 · another reportOur capture |
| Claude Opus 5.522 Sep 2026 | Claude Codehighest-available effort, max effort in the post's FrontierCode 2.0 chart | 45.5% | Introducing Claude Fable 5.2 and Claude Mythos 5.2Corroborated The same number is printed in 2 other documents: 1 2Run by Cognition · mean@5, per the system card · reported laterScored before Cognition updated its cheating scanner to remove false positives and rescored all results on 11 Nov 2026 |
| Claude Opus 5.522 Sep 2026 | Claude Codelow effort | 14.7% | Introducing Claude Fable 5.2 and Claude Mythos 5.2Corroborated The same number is printed in 1 other document: 1Run by Cognition · mean@5, per the system card · reported later · another reportScored before Cognition updated its cheating scanner to remove false positives and rescored all results on 11 Nov 2026 |
| Claude Opus 5.522 Sep 2026 | Claude Codemedium effort | 30.1% | Introducing Claude Fable 5.2 and Claude Mythos 5.2Corroborated The same number is printed in 1 other document: 1Run by Cognition · mean@5, per the system card · reported later · another reportScored before Cognition updated its cheating scanner to remove false positives and rescored all results on 11 Nov 2026 |
| Claude Opus 5.522 Sep 2026 | Claude Codehigh effort | 34.5% | Introducing Claude Fable 5.2 and Claude Mythos 5.2Corroborated The same number is printed in 1 other document: 1Run by Cognition · mean@5, per the system card · reported later · another reportScored before Cognition updated its cheating scanner to remove false positives and rescored all results on 11 Nov 2026 |
| Claude Opus 5.522 Sep 2026 | Claude Codexhigh effort | 43.4% | Introducing Claude Fable 5.2 and Claude Mythos 5.2Corroborated The same number is printed in 1 other document: 1Run by Cognition · mean@5, per the system card · reported later · another reportScored before Cognition updated its cheating scanner to remove false positives and rescored all results on 11 Nov 2026 |
| Claude Opus 5.522 Sep 2026 | Claude Codemax effort | 47.3% | FrontierCode LeaderboardChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Cognition’s leaderboard, 18 Nov 2026 · another reportOur capture |
| GPT-6.2 Astra17 Nov 2026 | Harness not specifiedmax effort | 44.2% | Introducing GPT-6.2 Astra and SolCorroborated The same number is printed in 1 other document: 1Run by CognitionOur capture |
| GPT-6.2 Astra17 Nov 2026 | Harness not specifiedlow effort | 38.1% | Introducing GPT-6.2 Astra and SolChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Run by Cognition · another reportOur capture |
| GPT-6.2 Astra17 Nov 2026 | Harness not specifiedmedium effort | 42.2% | Introducing GPT-6.2 Astra and SolChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Run by Cognition · another reportOur capture |
| GPT-6.2 Astra17 Nov 2026 | Harness not specifiedhigh effort | 43.6% | Introducing GPT-6.2 Astra and SolChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Run by Cognition · another reportOur capture |
| GPT-6.2 Astra17 Nov 2026 | Harness not specifiedxhigh effort | 44.1% | Introducing GPT-6.2 Astra and SolChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Run by Cognition · another reportOur capture |
| GPT-6.2 Astra17 Nov 2026 | Codexmax effort | 44.2% | FrontierCode LeaderboardCorroborated The same number is printed in 1 other document: 1Cognition’s leaderboard, 18 Nov 2026 · another reportOur capture |
| GPT-6.2 Sol17 Nov 2026 | Harness not specifiedmax effort | 43.8% | Introducing GPT-6.2 Astra and SolCorroborated The same number is printed in 1 other document: 1Run by CognitionOur capture |
| GPT-6.2 Sol17 Nov 2026 | Harness not specifiedlow effort | 33.1% | Introducing GPT-6.2 Astra and SolChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Run by Cognition · another reportOur capture |
| GPT-6.2 Sol17 Nov 2026 | Harness not specifiedmedium effort | 38.3% | Introducing GPT-6.2 Astra and SolChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Run by Cognition · another reportOur capture |
| GPT-6.2 Sol17 Nov 2026 | Harness not specifiedhigh effort | 39.7% | Introducing GPT-6.2 Astra and SolChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Run by Cognition · another reportOur capture |
| GPT-6.2 Sol17 Nov 2026 | Harness not specifiedxhigh effort | 39.8% | Introducing GPT-6.2 Astra and SolChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Run by Cognition · another reportOur capture |
| GPT-6.2 Sol17 Nov 2026 | Codexmax effort | 43.8% | FrontierCode LeaderboardCorroborated The same number is printed in 1 other document: 1Cognition’s leaderboard, 18 Nov 2026 · another reportOur capture |
| GPT-6 Astra3 Sep 2026 | Harness not specifiedmax effort | 42.8% | Introducing GPT-6.2 Astra and SolCorroborated The same number is printed in 2 other documents: 1 2reported laterScored before Cognition updated its cheating scanner to remove false positives and rescored all results on 11 Nov 2026Our capture |
| GPT-6 Astra3 Sep 2026 | Harness not specifiedlow effort | 31.1% | Introducing GPT-6.2 Astra and SolCorroborated The same number is printed in 1 other document: 1Run by Cognition · reported later · another reportOur capture |
| GPT-6 Astra3 Sep 2026 | Harness not specifiedmedium effort | 36.8% | Introducing GPT-6.2 Astra and SolCorroborated The same number is printed in 1 other document: 1reported later · another reportScored before Cognition updated its cheating scanner to remove false positives and rescored all results on 11 Nov 2026Our capture |
| GPT-6 Astra3 Sep 2026 | Harness not specifiedhigh effort | 38.3% | Introducing GPT-6.2 Astra and SolCorroborated The same number is printed in 1 other document: 1reported later · another reportScored before Cognition updated its cheating scanner to remove false positives and rescored all results on 11 Nov 2026Our capture |
| GPT-6 Astra3 Sep 2026 | Harness not specifiedxhigh effort | 41.4% | Introducing GPT-6.2 Astra and SolCorroborated The same number is printed in 1 other document: 1reported later · another reportScored before Cognition updated its cheating scanner to remove false positives and rescored all results on 11 Nov 2026Our capture |
| GPT-6 Astra3 Sep 2026 | Codexmax effort | 44.0% | FrontierCode LeaderboardChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Cognition’s leaderboard, 18 Nov 2026 · another reportOur capture |
| Gemini 4 Carbon28 Oct 2026 | Antigravity CLIhigh effort | 42.6% | FrontierCode LeaderboardChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Cognition’s leaderboard, 18 Nov 2026Our capture |
| Claude Sonnet 5.528 Sep 2026 | Claude Codemax effort | 42.2% | FrontierCode LeaderboardChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Cognition’s leaderboard, 18 Nov 2026Our capture |
| GPT-6.1 Sol29 Sep 2026 | Harness not specifiedmax effort | 39.0% | Introducing GPT-6.2 Astra and SolChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.reported laterScored before Cognition updated its cheating scanner to remove false positives and rescored all results on 11 Nov 2026Our capture |
| GPT-6.1 Sol29 Sep 2026 | Harness not specifiedlow effort | 25.6% | Introducing GPT-6.2 Astra and SolChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.reported later · another reportScored before Cognition updated its cheating scanner to remove false positives and rescored all results on 11 Nov 2026Our capture |
| GPT-6.1 Sol29 Sep 2026 | Harness not specifiedmedium effort | 29.6% | Introducing GPT-6.2 Astra and SolChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.reported later · another reportScored before Cognition updated its cheating scanner to remove false positives and rescored all results on 11 Nov 2026Our capture |
| GPT-6.1 Sol29 Sep 2026 | Harness not specifiedhigh effort | 34.8% | Introducing GPT-6.2 Astra and SolChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.reported later · another reportScored before Cognition updated its cheating scanner to remove false positives and rescored all results on 11 Nov 2026Our capture |
| GPT-6.1 Sol29 Sep 2026 | Harness not specifiedxhigh effort | 32.3% | Introducing GPT-6.2 Astra and SolChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.reported later · another reportScored before Cognition updated its cheating scanner to remove false positives and rescored all results on 11 Nov 2026Our capture |
| GPT-6.1 Sol29 Sep 2026 | Codexmax effort | 39.6% | FrontierCode LeaderboardChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Cognition’s leaderboard, 18 Nov 2026 · another reportOur capture |
| Gemini 4 Hydrogen12 Nov 2026 | Antigravity CLIxhigh effort | 38.9% | FrontierCode LeaderboardChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Cognition’s leaderboard, 18 Nov 2026Our capture |
| GPT-6 Sol22 Sep 2026 | Codexmax effort | 34.9% | FrontierCode LeaderboardChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Cognition’s leaderboard, 18 Nov 2026Our capture |
| Claude Fable 5.11 Sep 2026 | Claude Codexhigh effort | 32.4% | Introducing Claude Fable 5.2 and Claude Mythos 5.2Corroborated The same number is printed in 1 other document: 1Run by Cognition · mean@5, per the system card · reported laterScored before Cognition updated its cheating scanner to remove false positives and rescored all results on 11 Nov 2026 |
| Claude Fable 5.11 Sep 2026 | Claude Codelow effort | 20.6% | Introducing Claude Fable 5.2 and Claude Mythos 5.2Checked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Run by Cognition · mean@5, per the system card · reported later · another reportScored before Cognition updated its cheating scanner to remove false positives and rescored all results on 11 Nov 2026 |
| Claude Fable 5.11 Sep 2026 | Claude Codemedium effort | 21.5% | Introducing Claude Fable 5.2 and Claude Mythos 5.2Checked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Run by Cognition · mean@5, per the system card · reported later · another reportScored before Cognition updated its cheating scanner to remove false positives and rescored all results on 11 Nov 2026 |
| Claude Fable 5.11 Sep 2026 | Claude Codehigh effort | 25.7% | Introducing Claude Fable 5.2 and Claude Mythos 5.2Checked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Run by Cognition · mean@5, per the system card · reported later · another reportScored before Cognition updated its cheating scanner to remove false positives and rescored all results on 11 Nov 2026 |
| Claude Fable 5.11 Sep 2026 | Claude Codemax effort | 31.7% | Introducing Claude Fable 5.2 and Claude Mythos 5.2Corroborated The same number is printed in 1 other document: 1Run by Cognition · mean@5, per the system card · reported later · another reportScored before Cognition updated its cheating scanner to remove false positives and rescored all results on 11 Nov 2026 |
| Claude Fable 5.11 Sep 2026 | Claude Codexhigh effort | 34.0% | FrontierCode LeaderboardChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Cognition’s leaderboard, 18 Nov 2026 · another reportOur capture |
| Claude Haiku 5.57 Oct 2026 | Claude Codemax effort | 28.9% | FrontierCode LeaderboardChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Cognition’s leaderboard, 18 Nov 2026Our capture |
| GPT-5.6 Sol9 Jul 2026 | Codexmax effort | 28.9% | FrontierCode LeaderboardChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Cognition’s leaderboard, 18 Nov 2026Our capture |
| Claude Opus 524 Jul 2026 | Claude Codehigh effort | 28.1% | FrontierCode LeaderboardChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Cognition’s leaderboard, 18 Nov 2026Our capture |
| Gemini 4 Argon30 Sep 2026 | Devin CLIhigh effort | 27.6% | FrontierCode LeaderboardChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Cognition’s leaderboard, 18 Nov 2026Our capture |
| Muse Ember9 Nov 2026 | Stirrupmax reasoning effort | 27.2% | Introducing Our Smallest, Most Efficient Model: Muse EmberChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Run by Artificial Analysis · 3 attempts per task, averaged, per Artificial Analysis’s methodology · 500-turn cap, per Artificial Analysis’s methodology · GPT-6 Luna (medium) LLM judge, per Artificial Analysis’s methodology · Setting from Artificial Analysis’s methodologyOur capture |
| SWE-210 Sep 2026 | Devin CLIhigh effort | 24.1% | FrontierCode LeaderboardChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Cognition’s leaderboard, 18 Nov 2026Our capture |
| SWE-2 Flash4 Nov 2026 | Devin CLImax effort | 24.0% | FrontierCode LeaderboardChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Cognition’s leaderboard, 18 Nov 2026Our capture |
| GPT-5.523 Apr 2026 | Codexxhigh effort | 23.6% | FrontierCode LeaderboardChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Cognition’s leaderboard, 18 Nov 2026Our capture |
| GPT-6 Luna22 Sep 2026 | Codexmax effort | 22.7% | FrontierCode LeaderboardChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Cognition’s leaderboard, 18 Nov 2026Our capture |
| Inkling 2 Small5 Nov 2026 | Devin CLImax effort | 22.6% | FrontierCode LeaderboardChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Cognition’s leaderboard, 18 Nov 2026Our capture |
| DeepSeek-V4.1-Flash-101717 Oct 2026 | Devin CLImax effort | 20.2% | FrontierCode LeaderboardChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Cognition’s leaderboard, 18 Nov 2026Our capture |
| GLM-5.314 Aug 2026 | Devin CLImax effort | 20.2% | FrontierCode LeaderboardChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Cognition’s leaderboard, 18 Nov 2026Our capture |
| Kimi K3.1 Pro24 Oct 2026 | Devin CLImax effort | 19.9% | FrontierCode LeaderboardChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Cognition’s leaderboard, 18 Nov 2026Our capture |
| Mistral Large 46 Oct 2026 | Mistral Vibehigh effort | 19.7% | FrontierCode LeaderboardChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Cognition’s leaderboard, 18 Nov 2026Our capture |
| Kimi K316 Jul 2026 | Devin CLIhigh effort | 18.9% | FrontierCode LeaderboardChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Cognition’s leaderboard, 18 Nov 2026Our capture |
| SWE-1.78 Jul 2026 | Devin CLIEffort not specified | 15.5% | FrontierCode LeaderboardChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Cognition’s leaderboard, 18 Nov 2026Our capture |
| Claude Opus 4.828 May 2026 | Claude Codemax effort | 15.3% | FrontierCode LeaderboardChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Cognition’s leaderboard, 18 Nov 2026Our capture |
| GLM-5.3-Flash26 Aug 2026 | Devin CLImax effort | 14.9% | FrontierCode LeaderboardChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Cognition’s leaderboard, 18 Nov 2026Our capture |
| SWE-1.67 Apr 2026 | Devin CLIEffort not specified | 1.3% | FrontierCode LeaderboardChecked A person checked this number against its source on 20 Nov 2026. This confirms the number matches what the lab published. It doesn't confirm that the score was reproduced.Cognition’s leaderboard, 18 Nov 2026Our capture |