Okapi Bench: API Freshness
Models write integrations for changing APIs. The grader checks whether their calls still work with the current interfaces.
Kaggle publishes scores for 34 distinct model versions.
- Made by
- Okapi
- Released
- November 2026
- Kind
- Function-level problems
- Level
- University
- Scored
- Checked automatically
- Answers
- Code
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Run by
- Anyone
- Strongest model tested
- GPT-6 Astra #4 on the capability index
- Last model added
- October 2026
- Scores refreshed
- November 20th, 2026
GPT-6 Astra leads with 66.7%
Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.
- 66.7 GPT-6 Astra
- 62.5 GPT-6 Sol
- 62.5 GPT-6.1 Sol
- 60.4 GPT-5.6 Sol
- 60.4 Claude Sonnet 5.5
- 58.3 GPT-5.6 Terra
- 58.3 Claude Opus 5.5
- 56.3 GPT-5.6 Luna
- 56.3 GPT-6 Luna
- 54.2 Claude Haiku 5.5
- 52.1
Gemini 4 Argon
- 50.0 Claude Opus 5
- 41.7 GPT-5.5
- 37.5 Claude Opus 4.7
- 33.3 Claude Opus 4.8
- 31.3 GPT-5.4
- 31.3
Gemini 3.5 Flash-Lite
- 31.3
Gemini 3.8 Flash
- 29.2
Gemini 3.1 Pro
- 29.2 Claude Sonnet 5
- 27.1 Claude Opus 4.5
- 27.1 Claude Sonnet 4.6
- 27.1
Gemini 3.6 Flash
- 25.0
Gemini 3 Flash
- 22.9 Claude Haiku 4.5
- 22.9 Claude Opus 4.6
- 20.8 GPT-5.4 Nano
- 20.8
Gemma 4 26B A4B
- 18.8
Gemma 4 31B IT
- 16.7
Gemini 2.5 Pro
- 16.7 GPT-5.4 Mini
- 14.6
Gemini 2.5 Flash
- 14.6
Gemini 3.1 Flash-Lite
- 10.4 gpt-oss-120b
- 1 GPT-6 Astra 66.7%
- 2 GPT-6 Sol 62.5%
- 3 GPT-6.1 Sol 62.5%
- 4 GPT-5.6 Sol 60.4%
- 5 Claude Sonnet 5.5 60.4%
- 6 GPT-5.6 Terra 58.3%
- 7 Claude Opus 5.5 58.3%
- 8 GPT-5.6 Luna 56.3%
- 9 GPT-6 Luna 56.3%
- 10 Claude Haiku 5.5 54.2%
- 11
Gemini 4 Argon 52.1%
- 12 Claude Opus 5 50%
- 13 GPT-5.5 41.7%
- 14 Claude Opus 4.7 37.5%
- 15 Claude Opus 4.8 33.3%
- 16 GPT-5.4 31.3%
- 17
Gemini 3.5 Flash-Lite 31.3%
- 18
Gemini 3.8 Flash 31.3%
- 19
Gemini 3.1 Pro 29.2%
- 20 Claude Sonnet 5 29.2%
- 21 Claude Opus 4.5 27.1%
- 22 Claude Sonnet 4.6 27.1%
- 23
Gemini 3.6 Flash 27.1%
- 24
Gemini 3 Flash 25%
- 25 Claude Haiku 4.5 22.9%
- 26 Claude Opus 4.6 22.9%
- 27 GPT-5.4 Nano 20.8%
- 28
Gemma 4 26B A4B 20.8%
- 29
Gemma 4 31B IT 18.8%
- 30
Gemini 2.5 Pro Jun 2025 16.7%
- 31 GPT-5.4 Mini 16.7%
- 32
Gemini 2.5 Flash Sep 2025 14.6%
- 33
Gemini 3.1 Flash-Lite 14.6%
- 34 gpt-oss-120b 10.4%
Source: Official Okapi Bench: API Freshness leaderboard
| # | Model | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | GPT-6 Astra | 66.7% | Sep 2026 | Nov 2026 | Official leaderboard | |
| 2 | GPT-6 Sol | 62.5% | Sep 2026 | Nov 2026 | Official leaderboard | |
| 3 | GPT-6.1 Sol | 62.5% | Sep 2026 | Nov 2026 | Official leaderboard | |
| 4 | GPT-5.6 Sol | 60.4% | Jul 2026 | Nov 2026 | Official leaderboard | |
| 5 | Claude Sonnet 5.5 | 60.4% | Sep 2026 | Nov 2026 | Official leaderboard | |
| 6 | GPT-5.6 Terra | 58.3% | Jul 2026 | Nov 2026 | Official leaderboard | |
| 7 | Claude Opus 5.5 | 58.3% | Sep 2026 | Nov 2026 | Official leaderboard | |
| 8 | GPT-5.6 Luna | 56.3% | Jul 2026 | Nov 2026 | Official leaderboard | |
| 9 | GPT-6 Luna | 56.3% | Sep 2026 | Nov 2026 | Official leaderboard | |
| 10 | Claude Haiku 5.5 | 54.2% | Oct 2026 | Nov 2026 | Official leaderboard | |
| 11 | | 52.1% | Sep 2026 | Nov 2026 | Official leaderboard | |
| 12 | Claude Opus 5 | 50% | Jul 2026 | Nov 2026 | Official leaderboard | |
| 13 | GPT-5.5 | 41.7% | Apr 2026 | Nov 2026 | Official leaderboard | |
| 14 | Claude Opus 4.7 | 37.5% | Apr 2026 | Nov 2026 | Official leaderboard | |
| 15 | Claude Opus 4.8 | 33.3% | May 2026 | Nov 2026 | Official leaderboard | |
| 16 | GPT-5.4 | 31.3% | Mar 2026 | Nov 2026 | Official leaderboard | |
| 17 | | 31.3% | Jul 2026 | Nov 2026 | Official leaderboard | |
| 18 | | 31.3% | Sep 2026 | Nov 2026 | Official leaderboard | |
| 19 | | 29.2% | Feb 2026 | Nov 2026 | Official leaderboard | |
| 20 | Claude Sonnet 5 | 29.2% | Jun 2026 | Nov 2026 | Official leaderboard | |
| 21 | Claude Opus 4.5 | 27.1% | Nov 2025 | Nov 2026 | Official leaderboard | |
| 22 | Claude Sonnet 4.6 | 27.1% | Feb 2026 | Nov 2026 | Official leaderboard | |
| 23 | | 27.1% | Jul 2026 | Nov 2026 | Official leaderboard | |
| 24 | | 25% | Dec 2025 | Nov 2026 | Official leaderboard | |
| 25 | Claude Haiku 4.5 | 22.9% | Oct 2025 | Nov 2026 | Official leaderboard | |
| 26 | Claude Opus 4.6 | 22.9% | Feb 2026 | Nov 2026 | Official leaderboard | |
| 27 | GPT-5.4 Nano | 20.8% | Mar 2026 | Nov 2026 | Official leaderboard | |
| 28 | | 20.8% | Apr 2026 | Nov 2026 | Official leaderboard | |
| 29 | | 18.8% | Apr 2026 | Nov 2026 | Official leaderboard | |
| 30 | | 16.7% | Jun 2025 | Nov 2026 | Official leaderboard | |
| 31 | GPT-5.4 Mini | 16.7% | Mar 2026 | Nov 2026 | Official leaderboard | |
| 32 | | 14.6% | Sep 2025 | Nov 2026 | Official leaderboard | |
| 33 | | 14.6% | Mar 2026 | Nov 2026 | Official leaderboard | |
| 34 | gpt-oss-120b | 10.4% | Aug 2025 | Nov 2026 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Okapi Bench: API Freshness leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Okapi Bench: API Freshness 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 Coding
- SWE-bench Verified In use 500 human-validated GitHub issues from 12 Python repos. Agent writes a patch that must pass hidden tests. Claude Opus 4.7 83.5%
- LiveCodeBench v6 In use Competitive programming problems collected after model cutoffs from LeetCode, AtCoder, Codeforces. Scored pass@1 on hidden tests.
DeepSeek-V4-Pro 93.5%
- SWE-bench Multilingual In use 300 GitHub-issue tasks across nine programming languages in SWE-bench format. Patch graded by repository tests. Claude Fable 5.2 96.6%
- DeepSWE In use 113 original long-horizon engineering tasks across 91 repos and five languages, written from scratch. Hand-written verifiers accept alternative solutions. GPT-6 Astra 74.1%
- SciCode In use Scientist-curated research coding problems split into subproblems across natural sciences. Code checked against test cases.
Seed2.1 Pro 59.8%
- Codeforces rating In use Model solves recent Codeforces contest problems. An Elo-style rating is computed from simulated contest performance.
DeepSeek V4.1 Flash 3,471
Data audit
All 11 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 5 pass
- Pass Independent runs Scores from the official leaderboard (34 entries).
- Pass Models scored 34 models we track.
- Pass Newest score The newest is from October 2026, for Claude Haiku 5.5.
- Pass Frontier models 5 of the top 10 have a score, led by GPT-6 Astra (#4).
- Pass Headroom The best is 66.7%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on kaggle.com: 34 rows for models we track at the last read.
- Pass Last read November 20th, 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.