SAGE v1.1 (Vals)
Version 1.1
The official leaderboard hasn’t scored a model released after Inkling 2 Small (November 2026). Labs report their own numbers for one newer model: Inkling 2 Mini at 85.9%.
Models grade handwritten undergraduate math and computer science work against rubrics. Scored by class-balanced accuracy of each rubric check against expert grading.
Vals changed the metric from v1, which moved strict graders up and lenient ones down. 545 tests in five suites. The board had 28 models on October 27th, 2026.
- Made by
- Vals AI
- Released
- October 2026
- Kind
- Other
- Level
- University
- Scored
- Graded by people
- Answers
- Open-ended
- Tasks
- Kept private
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Items from
- Exams and contests, Real work and use
- Refresh
- New versions replace it
- Run by
- A host
- Based on
- SAGE (Vals)
- Strongest model tested
- Claude Opus 5.5 #5 on the capability index
- Last in a launch post
- November 2026
- Last model added
- November 2026
- Scores refreshed
- November 19th, 2026
Claude Opus 5.5 leads with 91.3%
Best score per model from the benchmark's own leaderboard, read on November 19th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart.
Claude Opus 5.5 leads with 91.3%, 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. Striped bars are claims, and dotted bars are reruns by Epoch AI or another board.
- 91.3 Claude Opus 5.5
- 90.5 GPT-6.1 Sol
- 89.8 Claude Haiku 5.5
- 89.5
Gemini 4 Argon
- 89.3 GLM-5.3-Flash
- 89.2
Qwen3.7-Plus
- 88.7 Grok 4.7
- 88.6
Inkling 2 Small
- 88.2
Gemini 3.8 Flash
- 88.0 Claude Sonnet 5.5
- 87.0 GPT-5.6 Terra
- 86.8 Kimi K3
- 86.4
Ember-1
- 85.8
Muse Spark Open
- 85.5
Qwen3.5 397B-A17B
- 85.5
MiniMax-M3
- 85.4
DeepSeek V4.1 Flash
- 85.3
MiniMax-M3.1-Flash
- 84.9
Qwen 3.5 Flash (hosted 35B-A3B)
- 84.5 MiMo-V2.6 Pro
- 83.4 GPT-6 Luna
- 83.3 MiMo-V2.6 Flash
- 83.2
Gemini 3.1 Pro
- 82.8
Gemma 4 31B IT
- 81.8
Qwen 3.8 Max
- 79.5
Gemini 3.5 Flash-Lite
- 74.5 Grok 4.1 Fast
- 72.0
Mistral Medium 3.5
- 59.2
Mistral Small 4
- 1 Claude Opus 5.5 91.3%
- 2 GPT-6.1 Sol 90.5%
- 3 Claude Haiku 5.5 89.8%
- 4
Gemini 4 Argon 89.5%
- 5 GLM-5.3-Flash 89.3%
- 6
Qwen3.7-Plus 89.2%
- 7 Grok 4.7 88.7%
- 8
Inkling 2 Small 88.6%
- 9
Gemini 3.8 Flash 88.2%
- 10 Claude Sonnet 5.5 88%
- 11 GPT-5.6 Terra 87%
- 12 Kimi K3 86.8%
- 13
Ember-1 86.4%
- 14
Muse Spark Open 85.8%
- 15
Qwen3.5 397B-A17B 85.5%
- 16
MiniMax-M3 85.5%
- 17
DeepSeek V4.1 Flash 85.4%
- 18
MiniMax-M3.1-Flash 85.3%
- 19
Qwen 3.5 Flash (hosted 35B-A3B) 84.9%
- 20 MiMo-V2.6 Pro 84.5%
- 21 GPT-6 Luna 83.4%
- 22 MiMo-V2.6 Flash 83.3%
- 23
Gemini 3.1 Pro 83.2%
- 24
Gemma 4 31B IT 82.8%
- 25
Qwen 3.8 Max 81.8%
- 26
Gemini 3.5 Flash-Lite 79.5%
- 27 Grok 4.1 Fast reasoning 74.5%
- 28
Mistral Medium 3.5 72%
- 29
Mistral Small 4 59.2%
Source: Official SAGE v1.1 (Vals) leaderboard
- 91.3 Claude Opus 5.5
- 90.5 GPT-6.1 Sol
- 89.8 Claude Haiku 5.5
- 89.5
Gemini 4 Argon
- 89.3 GLM-5.3-Flash
- 89.2
Qwen3.7-Plus
- 88.7 Grok 4.7
- 88.6
Inkling 2 Small
- 88.2
Gemini 3.8 Flash
- 88.0 Claude Sonnet 5.5
- 87.0 GPT-5.6 Terra
- 86.8 Kimi K3
- 86.4
Ember-1
- 85.9
Inkling 2 Mini
- 85.8
Muse Spark Open
- 85.5
Qwen3.5 397B-A17B
- 85.5
MiniMax-M3
- 85.4
DeepSeek V4.1 Flash
- 85.3
MiniMax-M3.1-Flash
- 84.9
Qwen 3.5 Flash (hosted 35B-A3B)
- 84.5 MiMo-V2.6 Pro
- 83.4 GPT-6 Luna
- 83.3 MiMo-V2.6 Flash
- 83.2
Gemini 3.1 Pro
- 82.8
Gemma 4 31B IT
- 81.8
Qwen 3.8 Max
- 79.5
Gemini 3.5 Flash-Lite
- 74.5 Grok 4.1 Fast
- 72.0
Mistral Medium 3.5
- 59.2
Mistral Small 4
- 1 Claude Opus 5.5 91.3%
- 2 GPT-6.1 Sol 90.5%
- 3 Claude Haiku 5.5 89.8%
- 4
Gemini 4 Argon 89.5%
- 5 GLM-5.3-Flash 89.3%
- 6
Qwen3.7-Plus 89.2%
- 7 Grok 4.7 88.7%
- 8
Inkling 2 Small 88.6%
- 9
Gemini 3.8 Flash 88.2%
- 10 Claude Sonnet 5.5 88%
- 11 GPT-5.6 Terra 87%
- 12 Kimi K3 86.8%
- 13
Ember-1 86.4%
- 14
Inkling 2 Mini 85.9%
- 15
Muse Spark Open 85.8%
- 16
Qwen3.5 397B-A17B 85.5%
- 17
MiniMax-M3 85.5%
- 18
DeepSeek V4.1 Flash 85.4%
- 19
MiniMax-M3.1-Flash 85.3%
- 20
Qwen 3.5 Flash (hosted 35B-A3B) 84.9%
- 21 MiMo-V2.6 Pro 84.5%
- 22 GPT-6 Luna 83.4%
- 23 MiMo-V2.6 Flash 83.3%
- 24
Gemini 3.1 Pro 83.2%
- 25
Gemma 4 31B IT 82.8%
- 26
Qwen 3.8 Max 81.8%
- 27
Gemini 3.5 Flash-Lite 79.5%
- 28 Grok 4.1 Fast reasoning 74.5%
- 29
Mistral Medium 3.5 72%
- 30
Mistral Small 4 59.2%
Sources: Official SAGE v1.1 (Vals) leaderboard and labs’ model cards
| # | Model | Score ± 95% CI | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | 91.3% ±2.7 | Sep 2026 | Official leaderboard | |
| 2 | GPT-6.1 Sol | 90.5% ±3 | Sep 2026 | Official leaderboard | |
| 3 | Claude Haiku 5.5 | 89.8% ±2.8 | Oct 2026 | Official leaderboard | |
| 4 | | 89.5% ±3.2 | Sep 2026 | Official leaderboard | |
| 5 | GLM-5.3-Flash | 89.3% ±3.4 | Aug 2026 | Official leaderboard | |
| 6 | | 89.2% ±2.7 | Jun 2026 | Official leaderboard | |
| 7 | Grok 4.7 | 88.7% ±3.5 | Sep 2026 | Official leaderboard | |
| 8 | | 88.6% ±3.4 | Nov 2026 | Official leaderboard | |
| 9 | | 88.2% ±3.4 | Sep 2026 | Official leaderboard | |
| 10 | Claude Sonnet 5.5 | 88% ±3.2 | Sep 2026 | Official leaderboard | |
| 11 | GPT-5.6 Terra | 87% ±3.9 | Jul 2026 | Official leaderboard | |
| 12 | Kimi K3 | 86.8% ±3.6 | Jul 2026 | Official leaderboard | |
| 13 | | 86.4% ±3.7 | Sep 2026 | Official leaderboard | |
| 14 | | 85.8% ±3.4 | Oct 2026 | Official leaderboard | |
| 15 | | 85.5% ±3.6 | Feb 2026 | Official leaderboard | |
| 16 | | 85.5% ±3.4 | Jun 2026 | Official leaderboard | |
| 17 | | 85.4% ±3.8 | Sep 2026 | Official leaderboard | |
| 18 | | 85.3% ±3.9 | Oct 2026 | Official leaderboard | |
| 19 | | 84.9% ±3.6 | Feb 2026 | Official leaderboard | |
| 20 | MiMo-V2.6 Pro | 84.5% ±3.7 | Sep 2026 | Official leaderboard | |
| 21 | GPT-6 Luna | 83.4% ±4.5 | Sep 2026 | Official leaderboard | |
| 22 | MiMo-V2.6 Flash | 83.3% ±4.2 | Sep 2026 | Official leaderboard | |
| 23 | | 83.2% ±3.8 | Feb 2026 | Official leaderboard | |
| 24 | | 82.8% ±4.1 | Apr 2026 | Official leaderboard | |
| 25 | | 81.8% ±4.1 | Aug 2026 | Official leaderboard | |
| 26 | | 79.5% ±4 | Jul 2026 | Official leaderboard | |
| 27 | Grok 4.1 Fast | 74.5% ±4.4 | reasoning | Nov 2025 | Official leaderboard |
| 28 | | 72% ±4.3 | Apr 2026 | Official leaderboard | |
| 29 | | 59.2% ±4.2 | Mar 2026 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | 91.3% | Sep 2026 | Official leaderboard | |
| 2 | GPT-6.1 Sol | 90.5% | Sep 2026 | Official leaderboard | |
| 3 | Claude Haiku 5.5 | 89.8% | Oct 2026 | Official leaderboard | |
| 4 | 89.5% | Sep 2026 | Official leaderboard | ||
| 5 | GLM-5.3-Flash | 89.3% | Aug 2026 | Official leaderboard | |
| 6 | 89.2% | Jun 2026 | Official leaderboard | ||
| 7 | Grok 4.7 | 88.7% | Sep 2026 | Official leaderboard | |
| 8 | 88.6% | Nov 2026 | Lab model card | ||
| 9 | 88.2% | Sep 2026 | Official leaderboard | ||
| 10 | Claude Sonnet 5.5 | 88% | Sep 2026 | Official leaderboard | |
| 11 | GPT-5.6 Terra | 87% | Jul 2026 | Official leaderboard | |
| 12 | Kimi K3 | 86.8% | Jul 2026 | Official leaderboard | |
| 13 | 86.4% | Sep 2026 | Official leaderboard | ||
| 14 | 85.9% | Nov 2026 | Lab model card | ||
| 15 | 85.8% | Oct 2026 | Official leaderboard | ||
| 16 | 85.5% | Feb 2026 | Official leaderboard | ||
| 17 | 85.5% | Jun 2026 | Official leaderboard | ||
| 18 | 85.4% | Sep 2026 | Official leaderboard | ||
| 19 | 85.3% | Oct 2026 | Official leaderboard | ||
| 20 | 84.9% | Feb 2026 | Official leaderboard | ||
| 21 | MiMo-V2.6 Pro | 84.5% | Sep 2026 | Official leaderboard | |
| 22 | GPT-6 Luna | 83.4% | Sep 2026 | Official leaderboard | |
| 23 | MiMo-V2.6 Flash | 83.3% | Sep 2026 | Official leaderboard | |
| 24 | 83.2% | Feb 2026 | Official leaderboard | ||
| 25 | 82.8% | Apr 2026 | Official leaderboard | ||
| 26 | 81.8% | Aug 2026 | Official leaderboard | ||
| 27 | 79.5% | Jul 2026 | Official leaderboard | ||
| 28 | Grok 4.1 Fast | 74.5% | reasoning | Nov 2025 | Official leaderboard |
| 29 | 72% | Apr 2026 | Official leaderboard | ||
| 30 | 59.2% | Mar 2026 | Official leaderboard |
Labs report scores for 2 models in their cards. Switch the scores above to rank them together.
The best score, 91.3%, costs $0.28 for the full run
Runs on the cost frontier score higher than any run that's cheaper. GLM-5.3-Flash comes within 2 points of the best for $0.006 for the full run, 44 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official SAGE v1.1 (Vals) leaderboard
| Model | Effort | Harness | Score | Cost of the full run | Output tokens |
|---|---|---|---|---|---|
| Claude Opus 5.5 | 91.3% | $0.28 | 10,157 | ||
| GPT-6.1 Sol | 90.5% | $0.08 | 2,237 | ||
| Claude Haiku 5.5 | 89.8% | $0.02 | 28,718 | ||
| 89.5% | $0.07 | 2,533 | |||
| GLM-5.3-Flash | 89.3% | $0.006 | 11,595 | ||
| 89.2% | $0.02 | 6,561 | |||
| Grok 4.7 | 88.7% | $0.11 | 11,295 | ||
| 88.6% | $0.02 | 10,882 | |||
| 88.2% | $0.08 | 9,377 | |||
| Claude Sonnet 5.5 | 88% | $0.16 | 12,190 | ||
| GPT-5.6 Terra | 87% | $0.11 | 4,266 | ||
| Kimi K3 | 86.8% | $0.23 | 5,583 | ||
| 86.4% | $0.21 | 4,053 | |||
| 85.8% | $0.07 | 4,090 | |||
| 85.5% | $0.01 | 8,922 | |||
| 85.5% | $0.01 | 5,435 | |||
| 85.4% | $0.01 | 7,114 | |||
| 85.3% | $0.008 | 5,865 | |||
| 84.9% | $0.006 | 8,945 | |||
| MiMo-V2.6 Pro | 84.5% | $0.02 | 6,261 | ||
| GPT-6 Luna | 83.4% | $0.006 | 5,652 | ||
| MiMo-V2.6 Flash | 83.3% | $0.007 | 8,391 | ||
| 83.2% | $0.05 | 3,679 | |||
| 82.8% | 3,349 | ||||
| 81.8% | $0.09 | 6,285 | |||
| 79.5% | $0.01 | 3,210 | |||
| Grok 4.1 Fast | reasoning | 74.5% | $0.005 | 1,100 | |
| 72% | $0.07 | 6,924 | |||
| 59.2% | $0.003 | 1,939 |
Number one over time Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official SAGE v1.1 (Vals) leaderboard
Qwen3.5 397B-A17B on the official leaderboard passed 85% in February 2026
Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.
Sources: Official SAGE v1.1 (Vals) leaderboard and labs’ model cards
One lab put it in a launch post in the last six months
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 |
|---|---|---|---|
| Nov 5, 2026 | 88.6 | SAGE v1.1, 88.6% |
One system card reports it
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 |
|---|---|---|---|---|
| Nov 20, 2026 | | 85.9 | SAGE v1.1 | Capabilities |
One lab claim next to the leaderboard
Each score a lab reported for its own model, beside the same model's best score on the leaderboard. Gaps mostly come from different harnesses, effort levels and task subsets. 1 of them match, which usually means one side copied the other. Every benchmark.
| Model | Lab says | Board says | Gap |
|---|---|---|---|
| | 88.6% SAGE v1.1, 88.6% | 88.6% Leaderboard | Same |
Versions
We switch the top row to each new version when it comes out. Open it for one row per version. An old version stays in play while people still test it, so whoever first takes it past 85% gets credit for closing it out.
Source: Official leaderboards
More in Other
- Artificial Analysis Intelligence Index v5 In use Version 5 of Artificial Analysis's index: nine evaluations in four equal categories, most with private test sets, run three times each in its own agent harness. Claude Fable 5.2 64.6
- Personal Superintelligence Index (Meta) In use Meta's composite of seven personal and knowledge-work evals: Agents' Last Exam, AutomationBench-AA, FocusBench, JobBench, GDP.pdf, VBT and DRACO.
- Vals Science Index In use Agents are scored on the equal average of BioMysteryBench, MysteryMechanism and Terminal-Bench-Science. GPT-6.2 Astra 68.4%
- Decision Index Public v0.3 In use Decision models return probabilities over labeled options in public tasks covering knowledge, language, retrieval, tools, and arts. A chance-corrected weighted aggregate combines the task scores. Granite Switch 4.1 30B 51.3
- MTEB Fading Massive Text Embedding Benchmark: retrieval, clustering, classification across languages and modalities.
Qwen3-Embedding-8B 72.2%
- SPEED-Bench Only in system cards Measures speculative decoding across varied prompts and domains. Reports the average acceptance length of draft tokens, so higher means faster generation at the same output.
Qwen3-Next-80B-A3B-Instruct 2.81
Data audit
All 11 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access The tasks are private.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Pass Independent runs Scores from the official leaderboard (29 entries), launch posts (1 score) and system cards (1 score).
- Pass Models scored 30 models we track.
- Pass Newest score The newest is from November 2026, for Inkling 2 Mini.
- Pass Frontier models 4 of the top 10 have a score, led by Claude Opus 5.5 (#5).
- Note Headroom Saturated. The best is 91.3%, past 85% since February 2026.
Leaderboard import 3 pass
- Pass Importer We read the board on vals.ai: 29 rows for models we track at the last read.
- Pass Last read November 19th, 2026.
- Pass Read worked The last read worked.
Consistency 2 pass
- Pass Lab claims The one pair agrees within 10 points.
- Pass Known issues No published audit found problems.