KRYT Benchmark
Models decide refund requests from transaction limits and event records. The grader checks policy compliance, valid actions, and consistency across rounds.
Kaggle publishes scores for 43 distinct model versions.
- Made by
- vaibhav lalwani
- Released
- October 2026
- Kind
- Customer service
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
- GPT-6 Astra #4 on the capability index
- Last model added
- October 2026
- Scores refreshed
- November 20th, 2026
23 models share the top score of 32% 23 models share the top score of 32%
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. 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.
- 32.0
Gemini 2.5 Pro
- 32.0 gpt-oss-20b
- 32.0
Gemini 2.5 Flash
- 32.0 Claude Haiku 4.5
- 32.0
Gemini 3 Flash
- 32.0 Claude Opus 4.6
- 32.0 GLM-5
- 32.0 Claude Sonnet 4.6
- 32.0 Grok 4.20
- 32.0
Gemini 3.1 Pro
- 32.0
Gemini 3.1 Flash-Lite
- 32.0 GPT-5.4
- 32.0
Gemma 4 26B A4B
- 32.0
Gemma 4 31B IT
- 32.0
Gemini 3.5 Flash
- 32.0 GPT-5.6 Luna
- 32.0 GPT-5.6 Sol
- 32.0
Gemini 3.6 Flash
- 32.0
Gemini 3.8 Flash
- 32.0 GPT-6 Luna
- 32.0 Claude Sonnet 5.5
- 32.0 GPT-6.1 Sol
- 32.0 Claude Haiku 5.5
- 31.0 gpt-oss-120b
- 31.0 Qwen 3 235B A22B Instruct 2506
- 28.0
DeepSeek-R1
- 28.0 GPT-5.4 Nano
- 27.0
Qwen3-Coder-480B-A35B
- 27.0 GPT-5.4 Mini
- 27.0
Gemini 3.5 Flash-Lite
- 27.0 Qwen 3 Next 80B Instruct
- 26.0 Claude Sonnet 5
- 25.0 Claude Opus 4.7
- 25.0 GPT-5.5
- 25.0 Claude Opus 5.5
- 24.0 Claude Opus 4.8
- 24.0 GPT-5.6 Terra
- 24.0 Claude Opus 5
- 24.0 GPT-6 Sol
- 23.0 Grok 4.5
- 23.0 Grok 4.6
- 23.0 GPT-6 Astra
- 1
Gemini 2.5 Pro Jun 2025 32%
- 2 gpt-oss-20b 32%
- 3
Gemini 2.5 Flash Sep 2025 32%
- 4 Claude Haiku 4.5 32%
- 5
Gemini 3 Flash 32%
- 6 Claude Opus 4.6 32%
- 7 GLM-5 32%
- 8 Claude Sonnet 4.6 32%
- 9 Grok 4.20 reasoning 32%
- 10
Gemini 3.1 Pro 32%
- 11
Gemini 3.1 Flash-Lite 32%
- 12 GPT-5.4 32%
- 13
Gemma 4 26B A4B 32%
- 14
Gemma 4 31B IT 32%
- 15
Gemini 3.5 Flash 32%
- 16 GPT-5.6 Luna 32%
- 17 GPT-5.6 Sol 32%
- 18
Gemini 3.6 Flash 32%
- 19
Gemini 3.8 Flash 32%
- 20 GPT-6 Luna 32%
- 21 Claude Sonnet 5.5 32%
- 22 GPT-6.1 Sol 32%
- 23 Claude Haiku 5.5 32%
- 24 gpt-oss-120b 31%
- 25 Qwen 3 235B A22B Instruct 2506 31%
- 26
DeepSeek-R1 May 2025 28%
- 27 GPT-5.4 Nano 28%
- 28
Qwen3-Coder-480B-A35B 27%
- 29 GPT-5.4 Mini 27%
- 30
Gemini 3.5 Flash-Lite 27%
- 31 Qwen 3 Next 80B Instruct 27%
- 32 Claude Sonnet 5 26%
- 33 Claude Opus 4.7 25%
- 34 GPT-5.5 25%
- 35 Claude Opus 5.5 25%
- 36 Claude Opus 4.8 24%
- 37 GPT-5.6 Terra 24%
- 38 Claude Opus 5 24%
- 39 GPT-6 Sol 24%
- 40 Grok 4.5 23%
- 41 Grok 4.6 23%
- 42 GPT-6 Astra 23%
Source: Official KRYT Benchmark leaderboard
- 32.0
Gemini 2.5 Pro
- 32.0 gpt-oss-20b
- 32.0
Gemini 2.5 Flash
- 32.0 Claude Haiku 4.5
- 32.0
Gemini 3 Flash
- 32.0 Claude Opus 4.6
- 32.0 GLM-5
- 32.0 Claude Sonnet 4.6
- 32.0 Grok 4.20
- 32.0
Gemini 3.1 Pro
- 32.0
Gemini 3.1 Flash-Lite
- 32.0 GPT-5.4
- 32.0
Gemma 4 26B A4B
- 32.0
Gemma 4 31B IT
- 32.0
Gemini 3.5 Flash
- 32.0 GPT-5.6 Luna
- 32.0 GPT-5.6 Sol
- 32.0
Gemini 3.6 Flash
- 32.0
Gemini 3.8 Flash
- 32.0 GPT-6 Luna
- 32.0 Claude Sonnet 5.5
- 32.0 GPT-6.1 Sol
- 32.0 Claude Haiku 5.5
- 31.0 gpt-oss-120b
- 28.0
DeepSeek-R1
- 28.0 GPT-5.4 Nano
- 27.0
Qwen3-Coder-480B-A35B
- 27.0 GPT-5.4 Mini
- 27.0
Gemini 3.5 Flash-Lite
- 26.0 Claude Sonnet 5
- 25.0 Claude Opus 4.7
- 25.0 GPT-5.5
- 25.0 Claude Opus 5.5
- 24.0 Claude Opus 4.8
- 24.0 GPT-5.6 Terra
- 24.0 Claude Opus 5
- 24.0 GPT-6 Sol
- 23.0 Grok 4.5
- 23.0 Grok 4.6
- 23.0 GPT-6 Astra
- 1
Gemini 2.5 Pro Jun 2025 32%
- 2 gpt-oss-20b 32%
- 3
Gemini 2.5 Flash Sep 2025 32%
- 4 Claude Haiku 4.5 32%
- 5
Gemini 3 Flash 32%
- 6 Claude Opus 4.6 32%
- 7 GLM-5 32%
- 8 Claude Sonnet 4.6 32%
- 9 Grok 4.20 reasoning 32%
- 10
Gemini 3.1 Pro 32%
- 11
Gemini 3.1 Flash-Lite 32%
- 12 GPT-5.4 32%
- 13
Gemma 4 26B A4B 32%
- 14
Gemma 4 31B IT 32%
- 15
Gemini 3.5 Flash 32%
- 16 GPT-5.6 Luna 32%
- 17 GPT-5.6 Sol 32%
- 18
Gemini 3.6 Flash 32%
- 19
Gemini 3.8 Flash 32%
- 20 GPT-6 Luna 32%
- 21 Claude Sonnet 5.5 32%
- 22 GPT-6.1 Sol 32%
- 23 Claude Haiku 5.5 32%
- 24 gpt-oss-120b 31%
- 25
DeepSeek-R1 May 2025 28%
- 26 GPT-5.4 Nano 28%
- 27
Qwen3-Coder-480B-A35B 27%
- 28 GPT-5.4 Mini 27%
- 29
Gemini 3.5 Flash-Lite 27%
- 30 Claude Sonnet 5 26%
- 31 Claude Opus 4.7 25%
- 32 GPT-5.5 25%
- 33 Claude Opus 5.5 25%
- 34 Claude Opus 4.8 24%
- 35 GPT-5.6 Terra 24%
- 36 Claude Opus 5 24%
- 37 GPT-6 Sol 24%
- 38 Grok 4.5 23%
- 39 Grok 4.6 23%
- 40 GPT-6 Astra 23%
Source: Official KRYT Benchmark leaderboard
| # | Entry | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | | 32% | Jun 2025 | Oct 2026 | Official leaderboard | |
| 2 | gpt-oss-20b | 32% | Aug 2025 | Oct 2026 | Official leaderboard | |
| 3 | | 32% | Sep 2025 | Oct 2026 | Official leaderboard | |
| 4 | Claude Haiku 4.5 | 32% | Oct 2025 | Oct 2026 | Official leaderboard | |
| 5 | | 32% | Dec 2025 | Oct 2026 | Official leaderboard | |
| 6 | Claude Opus 4.6 | 32% | Feb 2026 | Oct 2026 | Official leaderboard | |
| 7 | GLM-5 | 32% | Feb 2026 | Oct 2026 | Official leaderboard | |
| 8 | Claude Sonnet 4.6 | 32% | Feb 2026 | Oct 2026 | Official leaderboard | |
| 9 | Grok 4.20 | 32% | reasoning | Feb 2026 | Oct 2026 | Official leaderboard |
| 10 | | 32% | Feb 2026 | Oct 2026 | Official leaderboard | |
| 11 | | 32% | Mar 2026 | Oct 2026 | Official leaderboard | |
| 12 | GPT-5.4 | 32% | Mar 2026 | Oct 2026 | Official leaderboard | |
| 13 | | 32% | Apr 2026 | Oct 2026 | Official leaderboard | |
| 14 | | 32% | Apr 2026 | Oct 2026 | Official leaderboard | |
| 15 | | 32% | May 2026 | Oct 2026 | Official leaderboard | |
| 16 | GPT-5.6 Luna | 32% | Jul 2026 | Oct 2026 | Official leaderboard | |
| 17 | GPT-5.6 Sol | 32% | Jul 2026 | Oct 2026 | Official leaderboard | |
| 18 | | 32% | Jul 2026 | Oct 2026 | Official leaderboard | |
| 19 | | 32% | Sep 2026 | Oct 2026 | Official leaderboard | |
| 20 | GPT-6 Luna | 32% | Sep 2026 | Oct 2026 | Official leaderboard | |
| 21 | Claude Sonnet 5.5 | 32% | Sep 2026 | Oct 2026 | Official leaderboard | |
| 22 | GPT-6.1 Sol | 32% | Sep 2026 | Oct 2026 | Official leaderboard | |
| 23 | Claude Haiku 5.5 | 32% | Oct 2026 | Oct 2026 | Official leaderboard | |
| 24 | gpt-oss-120b | 31% | Aug 2025 | Oct 2026 | Official leaderboard | |
| 25 | Qwen 3 235B A22B Instruct 2506 | 31% | Oct 2026 | Official leaderboard | ||
| 26 | | 28% | May 2025 | Oct 2026 | Official leaderboard | |
| 27 | GPT-5.4 Nano | 28% | Mar 2026 | Oct 2026 | Official leaderboard | |
| 28 | | 27% | Jul 2025 | Oct 2026 | Official leaderboard | |
| 29 | GPT-5.4 Mini | 27% | Mar 2026 | Oct 2026 | Official leaderboard | |
| 30 | | 27% | Jul 2026 | Oct 2026 | Official leaderboard | |
| 31 | Qwen 3 Next 80B Instruct | 27% | Oct 2026 | Official leaderboard | ||
| 32 | Claude Sonnet 5 | 26% | Jun 2026 | Oct 2026 | Official leaderboard | |
| 33 | Claude Opus 4.7 | 25% | Apr 2026 | Oct 2026 | Official leaderboard | |
| 34 | GPT-5.5 | 25% | Apr 2026 | Oct 2026 | Official leaderboard | |
| 35 | Claude Opus 5.5 | 25% | Sep 2026 | Oct 2026 | Official leaderboard | |
| 36 | Claude Opus 4.8 | 24% | May 2026 | Oct 2026 | Official leaderboard | |
| 37 | GPT-5.6 Terra | 24% | Jul 2026 | Oct 2026 | Official leaderboard | |
| 38 | Claude Opus 5 | 24% | Jul 2026 | Oct 2026 | Official leaderboard | |
| 39 | GPT-6 Sol | 24% | Sep 2026 | Oct 2026 | Official leaderboard | |
| 40 | Grok 4.5 | 23% | Jul 2026 | Oct 2026 | Official leaderboard | |
| 41 | Grok 4.6 | 23% | Aug 2026 | Oct 2026 | Official leaderboard | |
| 42 | GPT-6 Astra | 23% | Sep 2026 | Oct 2026 | Official leaderboard |
| # | Model | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | | 32% | Jun 2025 | Oct 2026 | Official leaderboard | |
| 2 | gpt-oss-20b | 32% | Aug 2025 | Oct 2026 | Official leaderboard | |
| 3 | | 32% | Sep 2025 | Oct 2026 | Official leaderboard | |
| 4 | Claude Haiku 4.5 | 32% | Oct 2025 | Oct 2026 | Official leaderboard | |
| 5 | | 32% | Dec 2025 | Oct 2026 | Official leaderboard | |
| 6 | Claude Opus 4.6 | 32% | Feb 2026 | Oct 2026 | Official leaderboard | |
| 7 | GLM-5 | 32% | Feb 2026 | Oct 2026 | Official leaderboard | |
| 8 | Claude Sonnet 4.6 | 32% | Feb 2026 | Oct 2026 | Official leaderboard | |
| 9 | Grok 4.20 | 32% | reasoning | Feb 2026 | Oct 2026 | Official leaderboard |
| 10 | | 32% | Feb 2026 | Oct 2026 | Official leaderboard | |
| 11 | | 32% | Mar 2026 | Oct 2026 | Official leaderboard | |
| 12 | GPT-5.4 | 32% | Mar 2026 | Oct 2026 | Official leaderboard | |
| 13 | | 32% | Apr 2026 | Oct 2026 | Official leaderboard | |
| 14 | | 32% | Apr 2026 | Oct 2026 | Official leaderboard | |
| 15 | | 32% | May 2026 | Oct 2026 | Official leaderboard | |
| 16 | GPT-5.6 Luna | 32% | Jul 2026 | Oct 2026 | Official leaderboard | |
| 17 | GPT-5.6 Sol | 32% | Jul 2026 | Oct 2026 | Official leaderboard | |
| 18 | | 32% | Jul 2026 | Oct 2026 | Official leaderboard | |
| 19 | | 32% | Sep 2026 | Oct 2026 | Official leaderboard | |
| 20 | GPT-6 Luna | 32% | Sep 2026 | Oct 2026 | Official leaderboard | |
| 21 | Claude Sonnet 5.5 | 32% | Sep 2026 | Oct 2026 | Official leaderboard | |
| 22 | GPT-6.1 Sol | 32% | Sep 2026 | Oct 2026 | Official leaderboard | |
| 23 | Claude Haiku 5.5 | 32% | Oct 2026 | Oct 2026 | Official leaderboard | |
| 24 | gpt-oss-120b | 31% | Aug 2025 | Oct 2026 | Official leaderboard | |
| 25 | | 28% | May 2025 | Oct 2026 | Official leaderboard | |
| 26 | GPT-5.4 Nano | 28% | Mar 2026 | Oct 2026 | Official leaderboard | |
| 27 | | 27% | Jul 2025 | Oct 2026 | Official leaderboard | |
| 28 | GPT-5.4 Mini | 27% | Mar 2026 | Oct 2026 | Official leaderboard | |
| 29 | | 27% | Jul 2026 | Oct 2026 | Official leaderboard | |
| 30 | Claude Sonnet 5 | 26% | Jun 2026 | Oct 2026 | Official leaderboard | |
| 31 | Claude Opus 4.7 | 25% | Apr 2026 | Oct 2026 | Official leaderboard | |
| 32 | GPT-5.5 | 25% | Apr 2026 | Oct 2026 | Official leaderboard | |
| 33 | Claude Opus 5.5 | 25% | Sep 2026 | Oct 2026 | Official leaderboard | |
| 34 | Claude Opus 4.8 | 24% | May 2026 | Oct 2026 | Official leaderboard | |
| 35 | GPT-5.6 Terra | 24% | Jul 2026 | Oct 2026 | Official leaderboard | |
| 36 | Claude Opus 5 | 24% | Jul 2026 | Oct 2026 | Official leaderboard | |
| 37 | GPT-6 Sol | 24% | Sep 2026 | Oct 2026 | Official leaderboard | |
| 38 | Grok 4.5 | 23% | Jul 2026 | Oct 2026 | Official leaderboard | |
| 39 | Grok 4.6 | 23% | Aug 2026 | Oct 2026 | Official leaderboard | |
| 40 | GPT-6 Astra | 23% | Sep 2026 | Oct 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 KRYT Benchmark 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 KRYT Benchmark 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 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 Neon 56.3%
- 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%
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 (42 entries).
- Pass Models scored 40 models we track, plus 2 other entries on its leaderboard.
- Pass Newest score The newest is from October 2026, for Claude Haiku 5.5.
- Pass Frontier models 4 of the top 10 have a score, led by GPT-6 Astra (#4).
- Pass Headroom The best is 32%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on kaggle.com: 41 rows for models we track and 2 other entries 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.