GIM
Models solve problems that combine constraint tracking, reasoning, and communication using broadly accessible knowledge. Model judges score answers against task rubrics. An item response model adjusts for problem difficulty and judge effects to estimate ability.
The bank contains 615 public problems and 205 private problems. Comparable ability scores require a calibrated judge and the matching bank version.
- Released
- May 2026
- Kind
- Language reasoning
- Level
- Everyday
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- Public, plus a private test set
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- A host
- Strongest model tested
- GPT-5.4 Pro #19 on the capability index
- Last model added
- April 2026
- Scores refreshed
- November 18th, 2026
In the authors’ words
As LLM benchmarks saturate, the evaluation community has pursued two strategies to increase difficulty: escalating knowledge demands (GPQA, HLE) or removing knowledge entirely in favor of abstract reasoning (ARC-AGI). The first conflates memorization with capability; the second divorces reasoning from the practical contexts in which it matters. We take a different approach. The Grounded Integration Measure (GIM) is a benchmark of 820 original problems (615 public, 205 private) where difficulty comes from integration; individual problems require coordinating multiple cognitive operations (constraint satisfaction, state tracking, epistemic vigilance, audience calibration) over broadly accessible knowledge, so that reasoning stays grounded in realistic tasks without being gated on specialized expertise. Each problem is an original expert-authored composition, majority with rubric-decomposed scoring. We calibrate a judge-aware continuous response 2-parameter logistic (2PL) IRT model across 53 test-configurations (unique model x thinking-level pairs) and five calibrated judges, using 203,800 epoch-averaged prompt-judge cells derived from >1M raw judge-scored observations, producing robust ability estimates that correctly order test-configurations even when raw accuracy is distorted by errors, missing data, or judge leniency differences. Using this framework, we present a comprehensive leaderboard spanning 22 models and 47 reporting test-configurations, and conduct what is to our knowledge the most extensive published study of how test-time compute trades off against model capability on a fixed benchmark: 11 models swept across 35 test-configurations. We observe that within-family configuration choices, such as thinking budget and quantization, matter as much as model selection, and increasing thinking tokens has diminishing marginal returns.
GPT-5.4 Pro leads with 1.63 among models released by April 2026 GPT-5.4 Pro leads with 1.63 among models released by April 2026
Best score per entry from the benchmark's paper, read on November 18th, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.
The newest model with a score here came out in April 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 15 more
- 1.63 GPT-5.4 Pro
- 1.47
Gemini 3.1 Pro
- 1.29
Muse Spark
- 1.23 GPT-5.4
- 1.09 Claude Opus 4.7
- 1.06 Claude Opus 4.6
- 1.02 Muse Spark fp8
- 0.85 Claude Sonnet 4.6
- 0.58 GPT-5
- 0.17
Gemma 4 31B IT
- 0.09 Gemma 4 31B fp4
- 0.09 Gemma 4 31B fp8
- 0.01 Gemini 2.5 Pro (snapshot unspecified)
- -0.02 GPT-5.4 Mini
- -0.03
Gemini 3.1 Flash-Lite
- -0.56 gpt-oss-120b
- -0.63 Claude Opus 4
- -0.71 Claude Haiku 4.5
- -1.48
Llama 4 Maverick
- -1.53 GPT-4o (snapshot unspecified)
- -1.65
Llama 3.3 70B
- 1 GPT-5.4 Pro X-High 1.63
- 2
Gemini 3.1 Pro High 1.47
- 3
Muse Spark X-High 1.29
- 4 GPT-5.4 X-High 1.23
- 5 Claude Opus 4.7 High 1.09
- 6 Claude Opus 4.6 High 1.06
- 7 Muse Spark fp8 High 1.02
- 8 Claude Sonnet 4.6 High 0.85
- 9 GPT-5 High 0.58
- 10
Gemma 4 31B IT Medium 0.17
- 11 Gemma 4 31B fp4 Medium 0.09
- 12 Gemma 4 31B fp8 Medium 0.09
- 13 Gemini 2.5 Pro (snapshot unspecified) High 0.01
- 14 GPT-5.4 Mini High -0.02
- 15
Gemini 3.1 Flash-Lite High -0.03
- 16 gpt-oss-120b Medium -0.56
- 17 Claude Opus 4 High -0.63
- 18 Claude Haiku 4.5 High -0.71
- 19
Llama 4 Maverick OFF -1.48
- 20 GPT-4o (snapshot unspecified) OFF -1.53
- 21
Llama 3.3 70B OFF -1.65
Source: The GIM paper
- 1.63 GPT-5.4 Pro
- 1.47
Gemini 3.1 Pro
- 1.29
Muse Spark
- 1.23 GPT-5.4
- 1.09 Claude Opus 4.7
- 1.06 Claude Opus 4.6
- 0.85 Claude Sonnet 4.6
- 0.58 GPT-5
- 0.17
Gemma 4 31B IT
- -0.02 GPT-5.4 Mini
- -0.03
Gemini 3.1 Flash-Lite
- -0.56 gpt-oss-120b
- -0.63 Claude Opus 4
- -0.71 Claude Haiku 4.5
- -1.48
Llama 4 Maverick
- -1.65
Llama 3.3 70B
- 1 GPT-5.4 Pro X-High 1.63
- 2
Gemini 3.1 Pro High 1.47
- 3
Muse Spark X-High 1.29
- 4 GPT-5.4 X-High 1.23
- 5 Claude Opus 4.7 High 1.09
- 6 Claude Opus 4.6 High 1.06
- 7 Claude Sonnet 4.6 High 0.85
- 8 GPT-5 High 0.58
- 9
Gemma 4 31B IT Medium 0.17
- 10 GPT-5.4 Mini High -0.02
- 11
Gemini 3.1 Flash-Lite High -0.03
- 12 gpt-oss-120b Medium -0.56
- 13 Claude Opus 4 High -0.63
- 14 Claude Haiku 4.5 High -0.71
- 15
Llama 4 Maverick OFF -1.48
- 16
Llama 3.3 70B OFF -1.65
Source: The GIM paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.4 Pro | 1.63 | X-High | Mar 2026 | Official leaderboard |
| 2 | | 1.47 | High | Feb 2026 | Official leaderboard |
| 3 | | 1.29 | X-High | Apr 2026 | Official leaderboard |
| 4 | GPT-5.4 | 1.23 | X-High | Mar 2026 | Official leaderboard |
| 5 | Claude Opus 4.7 | 1.09 | High | Apr 2026 | Official leaderboard |
| 6 | Claude Opus 4.6 | 1.06 | High | Feb 2026 | Official leaderboard |
| 7 | Muse Spark fp8 | 1.02 | High | Official leaderboard | |
| 8 | Claude Sonnet 4.6 | 0.85 | High | Feb 2026 | Official leaderboard |
| 9 | GPT-5 | 0.58 | High | Aug 2025 | Official leaderboard |
| 10 | | 0.17 | Medium | Apr 2026 | Official leaderboard |
| 11 | Gemma 4 31B fp4 | 0.09 | Medium | Official leaderboard | |
| 12 | Gemma 4 31B fp8 | 0.09 | Medium | Official leaderboard | |
| 13 | Gemini 2.5 Pro (snapshot unspecified) | 0.01 | High | Official leaderboard | |
| 14 | GPT-5.4 Mini | -0.02 | High | Mar 2026 | Official leaderboard |
| 15 | | -0.03 | High | Mar 2026 | Official leaderboard |
| 16 | gpt-oss-120b | -0.56 | Medium | Aug 2025 | Official leaderboard |
| 17 | Claude Opus 4 | -0.63 | High | May 2025 | Official leaderboard |
| 18 | Claude Haiku 4.5 | -0.71 | High | Oct 2025 | Official leaderboard |
| 19 | | -1.48 | OFF | Apr 2025 | Official leaderboard |
| 20 | GPT-4o (snapshot unspecified) | -1.53 | OFF | Official leaderboard | |
| 21 | | -1.65 | OFF | Dec 2024 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.4 Pro | 1.63 | X-High | Mar 2026 | Official leaderboard |
| 2 | | 1.47 | High | Feb 2026 | Official leaderboard |
| 3 | | 1.29 | X-High | Apr 2026 | Official leaderboard |
| 4 | GPT-5.4 | 1.23 | X-High | Mar 2026 | Official leaderboard |
| 5 | Claude Opus 4.7 | 1.09 | High | Apr 2026 | Official leaderboard |
| 6 | Claude Opus 4.6 | 1.06 | High | Feb 2026 | Official leaderboard |
| 7 | Claude Sonnet 4.6 | 0.85 | High | Feb 2026 | Official leaderboard |
| 8 | GPT-5 | 0.58 | High | Aug 2025 | Official leaderboard |
| 9 | | 0.17 | Medium | Apr 2026 | Official leaderboard |
| 10 | GPT-5.4 Mini | -0.02 | High | Mar 2026 | Official leaderboard |
| 11 | | -0.03 | High | Mar 2026 | Official leaderboard |
| 12 | gpt-oss-120b | -0.56 | Medium | Aug 2025 | Official leaderboard |
| 13 | Claude Opus 4 | -0.63 | High | May 2025 | Official leaderboard |
| 14 | Claude Haiku 4.5 | -0.71 | High | Oct 2025 | Official leaderboard |
| 15 | | -1.48 | OFF | Apr 2025 | Official leaderboard |
| 16 | | -1.65 | OFF | Dec 2024 | Official leaderboard |
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: The GIM paper
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| GPT-5.4 Pro | X-High | 1.63 | |||
| GPT-5.4 Pro | High | 1.62 | |||
| GPT-5.4 Pro | Medium | 1.55 | |||
| High | 1.47 | ||||
| Medium | 1.35 | ||||
| X-High | 1.29 | ||||
| GPT-5.4 | X-High | 1.23 | |||
| GPT-5.4 | High | 1.21 | |||
| Claude Opus 4.7 | High | 1.09 | |||
| Claude Opus 4.6 | High | 1.06 | |||
| GPT-5.4 | Medium | 1.04 | |||
| Low | 1.03 | ||||
| Claude Sonnet 4.6 | High | 0.85 | |||
| Claude Opus 4.6 | Medium | 0.76 | |||
| GPT-5.4 | Low | 0.60 | |||
| Claude Sonnet 4.6 | Medium | 0.59 | |||
| GPT-5 | High | 0.58 | |||
| GPT-5 | Medium | 0.36 | |||
| Claude Sonnet 4.6 | Low | 0.20 | |||
| Medium | 0.17 | ||||
| Claude Opus 4.6 | Low | 0.14 | |||
| GPT-5.4 Mini | High | -0.02 | |||
| High | -0.03 | ||||
| GPT-5 | Low | -0.04 | |||
| GPT-5.4 Mini | Medium | -0.13 | |||
| gpt-oss-120b | Medium | -0.56 | |||
| Medium | -0.63 | ||||
| Claude Opus 4 | High | -0.63 | |||
| Claude Haiku 4.5 | High | -0.71 | |||
| GPT-5.4 Mini | Low | -0.76 | |||
| Claude Haiku 4.5 | Medium | -0.81 | |||
| Claude Opus 4 | Medium | -0.83 | |||
| non-thinking, OFF | -0.85 | ||||
| Low | -0.91 | ||||
| Claude Haiku 4.5 | Low | -0.91 | |||
| Claude Opus 4 | Low | -0.92 | |||
| OFF | -1.48 | ||||
| OFF | -1.65 |
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: The GIM paper
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| GPT-5.4 Pro | X-High | 1.63 | |||
| GPT-5.4 Pro | High | 1.62 | |||
| GPT-5.4 Pro | Medium | 1.55 | |||
| High | 1.47 | ||||
| Medium | 1.35 | ||||
| X-High | 1.29 | ||||
| GPT-5.4 | X-High | 1.23 | |||
| GPT-5.4 | High | 1.21 | |||
| Claude Opus 4.7 | High | 1.09 | |||
| Claude Opus 4.6 | High | 1.06 | |||
| GPT-5.4 | Medium | 1.04 | |||
| Low | 1.03 | ||||
| Claude Sonnet 4.6 | High | 0.85 | |||
| Claude Opus 4.6 | Medium | 0.76 | |||
| GPT-5.4 | Low | 0.60 | |||
| Claude Sonnet 4.6 | Medium | 0.59 | |||
| GPT-5 | High | 0.58 | |||
| GPT-5 | Medium | 0.36 | |||
| Claude Sonnet 4.6 | Low | 0.20 | |||
| Medium | 0.17 | ||||
| Claude Opus 4.6 | Low | 0.14 | |||
| GPT-5.4 Mini | High | -0.02 | |||
| High | -0.03 | ||||
| GPT-5 | Low | -0.04 | |||
| GPT-5.4 Mini | Medium | -0.13 | |||
| gpt-oss-120b | Medium | -0.56 | |||
| Medium | -0.63 | ||||
| Claude Opus 4 | High | -0.63 | |||
| Claude Haiku 4.5 | High | -0.71 | |||
| GPT-5.4 Mini | Low | -0.76 | |||
| Claude Haiku 4.5 | Medium | -0.81 | |||
| Claude Opus 4 | Medium | -0.83 | |||
| non-thinking, OFF | -0.85 | ||||
| Low | -0.91 | ||||
| Claude Haiku 4.5 | Low | -0.91 | |||
| Claude Opus 4 | Low | -0.92 | |||
| OFF | -1.48 | ||||
| OFF | -1.65 |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The GIM paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official GIM leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Knowledge
- MMLU-Pro In use Harder 10-option version of MMLU with reasoning-focused questions across 14 subjects.
Intern-S2-397B 89.8%
- MMLU In use 57-subject multiple-choice exam questions from elementary to professional level. Scored by accuracy.
Seed1.8 92.3%
- SuperGPQA In use 26,529 graduate-level multiple-choice questions across 285 disciplines. Accuracy.
Qwen 3.6 Max (Preview) 73.9%
- WideSearch In use 200 bilingual broad info-seeking tasks: agent collects many atomic facts into a table. Scored by success rate and row/item F1.
Tencent Hy4 preview 83.9%
- BBEH micro average In use Models solve harder replacements for each of the 23 BIG-Bench Hard tasks, 4,520 examples in total. The score is the share of all examples answered correctly.
Gemma 4 31B IT 74.4%
- HLE-Diamond In use Models answer 1,000 cleaned expert questions from Humanity's Last Exam, 500 on reasoning and 500 on knowledge, closed book. Graded on exact answers. Claude Fable 5.2 77.9%
Data audit
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 7 months ago, in April 2026, for Claude Opus 4.7. Every benchmark
Catalog record 2 pass
- Pass Task access Public tasks, plus a private test set.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the benchmark’s paper (21 entries).
- Pass Models scored 16 models we track, plus 5 other entries on its leaderboard.
- Warning Newest score The newest came 7 months ago, in April 2026, for Claude Opus 4.7.
- Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.4 Pro (#19).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 38 rows for models we track and 5 other entries at the last read.
- Pass Last read November 18th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.