UniCode
Models solve generated competitive programming problems using automated test cases. Harbor packages 399 problems with validated reference solutions.
The October 16, 2025 paper compared 19 models on 492 problems. OpenAI o4-mini led that release with a 70.3% pass rate.
- Made by
- Xinyue Zheng and colleagues
- Released
- October 2025
- Kind
- Competitive programming
- Level
- Competition
- Scored
- Checked automatically
- Answers
- Code
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Items from
- Generated
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
- GPT-5 #71 on the capability index
- Last model added
- September 2025
- Scores refreshed
- November 20th, 2026
o4-mini leads with 70.3% among models released by September 2025 o4-mini leads with 70.3% among models released by September 2025
Best score per entry from the benchmark's paper, read on November 20th, 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 September 2025, 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 16 more
- 70.3 o4-mini
- 67.7 GPT-5
- 61.6
Gemini 2.5 Pro
- 60.5
DeepSeek-V3.1
- 55.6 deepseek-r1 (snapshot unspecified)
- 55.1 o3-mini
- 53.5
Qwen3-235B-A22B
- 47.7
Gemini 2.5 Flash
- 46.4 Grok-3 mini
- 45.5 Claude 3.7 Sonnet
- 42.4 GPT-4.1 mini
- 36.5 GPT-4.1
- 35.4
Qwen3-Coder-480B-A35B
- 32.4 Claude Sonnet 4
- 26.2
Llama 4 Maverick
- 15.4 gpt-4o (snapshot unspecified)
- 13.4
Qwen2.5-Coder-32B
- 13.1
Gemma 3 27B
- 5.50 llama-3.3-8b-instruct
- 1 o4-mini high 70.3%
- 2 GPT-5 medium 67.7%
- 3
Gemini 2.5 Pro Jun 2025 61.6%
- 4
DeepSeek-V3.1 thinking 60.5%
- 5 deepseek-r1 (snapshot unspecified) 55.6%
- 6 o3-mini medium 55.1%
- 7
Qwen3-235B-A22B 53.5%
- 8
Gemini 2.5 Flash Sep 2025 47.7%
- 9 Grok-3 mini 46.4%
- 10 Claude 3.7 Sonnet 45.5%
- 11 GPT-4.1 mini 42.4%
- 12 GPT-4.1 36.5%
- 13
Qwen3-Coder-480B-A35B 35.4%
- 14 Claude Sonnet 4 32.4%
- 15
Llama 4 Maverick 26.2%
- 16 gpt-4o (snapshot unspecified) 15.4%
- 17
Qwen2.5-Coder-32B 13.4%
- 18
Gemma 3 27B 13.1%
- 19 llama-3.3-8b-instruct 5.50%
Source: The UniCode paper
- 1 o4-mini high 70.3%
- 2 GPT-5 medium 67.7%
- 3
Gemini 2.5 Pro Jun 2025 61.6%
- 4
DeepSeek-V3.1 thinking 60.5%
- 5 o3-mini medium 55.1%
- 6
Qwen3-235B-A22B 53.5%
- 7
Gemini 2.5 Flash Sep 2025 47.7%
- 8 Grok-3 mini 46.4%
- 9 Claude 3.7 Sonnet 45.5%
- 10 GPT-4.1 mini 42.4%
- 11 GPT-4.1 36.5%
- 12
Qwen3-Coder-480B-A35B 35.4%
- 13 Claude Sonnet 4 32.4%
- 14
Llama 4 Maverick 26.2%
- 15
Qwen2.5-Coder-32B 13.4%
- 16
Gemma 3 27B 13.1%
Source: The UniCode paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | o4-mini | 70.3% | high | Apr 2025 | Official leaderboard |
| 2 | GPT-5 | 67.7% | medium | Aug 2025 | Official leaderboard |
| 3 | | 61.6% | Jun 2025 | Official leaderboard | |
| 4 | | 60.5% | thinking | Aug 2025 | Official leaderboard |
| 5 | deepseek-r1 (snapshot unspecified) | 55.6% | Official leaderboard | ||
| 6 | o3-mini | 55.1% | medium | Jan 2025 | Official leaderboard |
| 7 | | 53.5% | Apr 2025 | Official leaderboard | |
| 8 | | 47.7% | Sep 2025 | Official leaderboard | |
| 9 | Grok-3 mini | 46.4% | Apr 2025 | Official leaderboard | |
| 10 | Claude 3.7 Sonnet | 45.5% | Feb 2025 | Official leaderboard | |
| 11 | GPT-4.1 mini | 42.4% | Apr 2025 | Official leaderboard | |
| 12 | GPT-4.1 | 36.5% | Apr 2025 | Official leaderboard | |
| 13 | | 35.4% | Jul 2025 | Official leaderboard | |
| 14 | Claude Sonnet 4 | 32.4% | May 2025 | Official leaderboard | |
| 15 | | 26.2% | Apr 2025 | Official leaderboard | |
| 16 | gpt-4o (snapshot unspecified) | 15.4% | Official leaderboard | ||
| 17 | | 13.4% | Sep 2024 | Official leaderboard | |
| 18 | | 13.1% | Mar 2025 | Official leaderboard | |
| 19 | llama-3.3-8b-instruct | 5.50% | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | o4-mini | 70.3% | high | Apr 2025 | Official leaderboard |
| 2 | GPT-5 | 67.7% | medium | Aug 2025 | Official leaderboard |
| 3 | | 61.6% | Jun 2025 | Official leaderboard | |
| 4 | | 60.5% | thinking | Aug 2025 | Official leaderboard |
| 5 | o3-mini | 55.1% | medium | Jan 2025 | Official leaderboard |
| 6 | | 53.5% | Apr 2025 | Official leaderboard | |
| 7 | | 47.7% | Sep 2025 | Official leaderboard | |
| 8 | Grok-3 mini | 46.4% | Apr 2025 | Official leaderboard | |
| 9 | Claude 3.7 Sonnet | 45.5% | Feb 2025 | Official leaderboard | |
| 10 | GPT-4.1 mini | 42.4% | Apr 2025 | Official leaderboard | |
| 11 | GPT-4.1 | 36.5% | Apr 2025 | Official leaderboard | |
| 12 | | 35.4% | Jul 2025 | Official leaderboard | |
| 13 | Claude Sonnet 4 | 32.4% | May 2025 | Official leaderboard | |
| 14 | | 26.2% | Apr 2025 | Official leaderboard | |
| 15 | | 13.4% | Sep 2024 | Official leaderboard | |
| 16 | | 13.1% | Mar 2025 | Official leaderboard |
Rankings by part
We read 3 parts from the benchmark’s paper: Easy, Medium and Hard. Each ranks models on one part of the test. o4-mini leads every one of them. Arrows show how far a model moved from its overall rank among the models we track.
Easy
16 models we track have a score here.
- 1 o4-mini 94.9%
- 2
Gemini 2.5 Pro Jun 2025 ↑1 94%
- 3 GPT-5 ↓1 89.5%
- 4
DeepSeek-V3.1 89.2%
- 5 o3-mini 86.2%
- 6
Gemini 2.5 Flash Sep 2025 ↑1 81.4%
- 7
Qwen3-235B-A22B ↓1 80.2%
- 8 Grok-3 mini 77.8%
- 9 Claude 3.7 Sonnet 76.2%
- 10 GPT-4.1 mini 73.7%
Medium
16 models we track have a score here.
- 1 o4-mini 78.2%
- 2 GPT-5 77.6%
- 3
DeepSeek-V3.1 ↑1 59.8%
- 4
Gemini 2.5 Pro Jun 2025 ↓1 53.1%
- 5 o3-mini 50%
- 6
Qwen3-235B-A22B 39.7%
- 7 Claude 3.7 Sonnet ↑2 24.1%
- 8
Gemini 2.5 Flash Sep 2025 ↓1 22.6%
- 9 GPT-4.1 ↑2 21.8%
- 10 Grok-3 mini ↓2 21.7%
Hard
16 models we track have a score here.
- 1 o4-mini 21.6%
- 2 GPT-5 18.8%
- 3
DeepSeek-V3.1 ↑1 11.5%
- 4
Gemini 2.5 Pro Jun 2025 ↓1 8.50%
- 5 o3-mini 6.00%
- 6
Qwen3-235B-A22B 5.10%
- 7
Gemini 2.5 Flash Sep 2025 4.80%
- 8 GPT-4.1 mini ↑2 3.80%
- 9 Grok-3 mini ↓1 3.30%
- 10 Claude 3.7 Sonnet ↓1 2.40%
The best score, 70.3%, costs $0.03 a task
Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: The UniCode paper
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| o4-mini | high | 70.3% | $0.03 | ||
| GPT-5 | medium | 67.7% | $0.04 | ||
| o4-mini | medium | 66.1% | $0.02 | ||
| 61.6% | $0.20 | ||||
| thinking | 60.5% | $0.03 | |||
| o3-mini | medium | 55.1% | $0.02 | ||
| 53.5% | $0.03 | ||||
| 49.8% | $0.007 | ||||
| 47.7% | $0.009 | ||||
| Grok-3 mini | 46.4% | $0.004 | |||
| Claude 3.7 Sonnet | 45.5% | $0.13 | |||
| GPT-4.1 mini | 42.4% | $0.007 | |||
| GPT-4.1 | 36.5% | $0.007 | |||
| 35.4% | $0.01 | ||||
| Claude Sonnet 4 | 32.4% | $0.02 | |||
| 26.2% | $0.0006 | ||||
| 13.4% | $0.004 | ||||
| 13.1% |
The best score, 70.3%, costs $0.03 a task
Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: The UniCode paper
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| o4-mini | high | 70.3% | $0.03 | ||
| GPT-5 | medium | 67.7% | $0.04 | ||
| o4-mini | medium | 66.1% | $0.02 | ||
| 61.6% | $0.20 | ||||
| thinking | 60.5% | $0.03 | |||
| o3-mini | medium | 55.1% | $0.02 | ||
| 53.5% | $0.03 | ||||
| 49.8% | $0.007 | ||||
| 47.7% | $0.009 | ||||
| Grok-3 mini | 46.4% | $0.004 | |||
| Claude 3.7 Sonnet | 45.5% | $0.13 | |||
| GPT-4.1 mini | 42.4% | $0.007 | |||
| GPT-4.1 | 36.5% | $0.007 | |||
| 35.4% | $0.01 | ||||
| Claude Sonnet 4 | 32.4% | $0.02 | |||
| 26.2% | $0.0006 | ||||
| 13.4% | $0.004 | ||||
| 13.1% |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The UniCode 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 UniCode 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
9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 14 months ago, in September 2025, for Gemini 2.5 Flash. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
- Pass Independent runs Scores from the benchmark’s paper (19 entries).
- Pass Models scored 16 models we track, plus 3 other entries on its leaderboard.
- Warning Newest score The newest came 14 months ago, in September 2025, for Gemini 2.5 Flash.
- Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5 (#71).
- Pass Headroom The best is 70.3%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 18 rows for models we track and 3 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.