Benchmark Almanac

CNMO 2024

Ring-1T 88.5% leads since Oct 2025 Dropped

Models answer problems from the 2024 Chinese National High School Mathematics Olympiad. DeepSeek reports Pass@1 averaged over 16 samples.

DeepSeek built the eval set from the contest and did not release its prepared version or problem count.

Made by Chinese Mathematical Society (contest) , DeepSeek (eval set) Released Dec 2024 Competition problems with answers Last in a launch post Jul 2025 , dropped after it saturated Last model added Jan 2026
Level
Competition The strongest students, in olympiad-style contests
Scored
Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
Answers
Short answer A number, word or short string matched to a key.
Paper cms.org.cn
6
Models scored in lab cards
6
Launch posts list it, from 4 labs
5
System cards report it, from 4 labs

Ring-1T leads with 88.5% among models released by Jan 2026

Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.

The newest model with a score here came out in Jan 2026, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 88.5 Ring-1T
  2. 86.9 DeepSeek-R1
  3. 83.7 Step 3
  4. 78.2 STEP3-VL-10B
  5. 74.3 Kimi K2
  6. 43.2 DeepSeek-V3
  1. 1 Ring-1T 88.5%
  2. 2 DeepSeek-R1 86.9%
  3. 3 Step 3 83.7%
  4. 4 STEP3-VL-10B 78.2%
  5. 5 Kimi K2 Jul 2025 74.3%
  6. 6 DeepSeek-V3 43.2%
#ModelScoreSettingDateSource
1 Ring-1T 88.5% Oct 2025 Model card
2 DeepSeek-R1 86.9% May 2025 Model card
3 Step 3 83.7% Jul 2025 Model card
4 STEP3-VL-10B 78.2% Jan 2026 Model card
5 Kimi K2 Jul 2025 74.3% Jul 2025 Model card
6 DeepSeek-V3 43.2% Dec 2024 Model card

3 models have held number one since its release in Dec 2024

Lab claims count from the day the card came out, independent runs from the model’s release.

DeepSeek Ant Group
Lab claims Passed 85% in May 2025, by DeepSeek-R1
Ring-1T 88.5%

The best score passed 85% in May 2025

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Reported by the lab in its model card Best so far
0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) Ring-1T DeepSeek-R1 DeepSeek-R1 DeepSeek-V3 0% 20% 40% 60% 80% 100% 2025 2026 Near the ceiling (85%) Ring-1T DeepSeek-R1

Labs dropped it from launch posts once the best score passed 85%

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.

DeepSeek
Baidu
Moonshot AI
StepFun
DateLaunch postScoreAs the post writes it
31 Jul 2025 Step 3 83.7 CNMO24
11 Jul 2025 Kimi K2 74.3 CNMO 2024, Avg@16
28 May 2025 DeepSeek-R1 86.9 CNMO 2024 (Pass@1)
16 Mar 2025 ERNIE 4.5 CNMO2024
20 Jan 2025 DeepSeek-R1 78.8 CNMO 2024 (Pass@1)
26 Dec 2024 DeepSeek-V3 43.2 CNMO 2024 (Pass@1)

5 system cards report it, from 4 labs

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.

DateDocumentScoreAs the document writes itSection
14 Jan 2026 STEP3-VL-10B technical report 78.2 CNMO2024, SeRe (Tables 2 and 3). PaCoRe 81.17 Capabilities
21 Oct 2025 Ring-1T technical report 88.5 CNMO 2024 (Table 1) Capabilities
21 Jul 2025 Kimi K2 technical report 74.3 CNMO 2024 (Avg@16) (Table 3) Capabilities
20 Jan 2025 DeepSeek-R1 technical report 78.8 CNMO 2024 (Pass@1), DeepSeek-R1 (Table 8, same as final column of Table 3) Capabilities
26 Dec 2024 DeepSeek-V3 technical report 43.2 CNMO 2024 (Pass@1), DeepSeek-V3 (Table 6) Capabilities

More in Math

All 105 in Math
  • IMO-AnswerBench In use 400 olympiad problems with short verifiable answers, robustified against memorization. Scored by answer match. GLM-5.2 91%
  • AIME 2026 In use Models solve the 30 integer-answer problems from the 2026 AIME I and II math competitions. Scored by exact answer match. GPT-5.5 100%
  • HMMT 2026 In use Models solve the 33 final-answer problems from the February 2026 Harvard-MIT Mathematics Tournament. Scored by exact answer match. GPT-5.5 98.5%
  • MathArena (Apex, IMO, USAMO) In use Evaluates models on newly released math competitions after release. Final-answer or human/LLM-judged proof scores. Claude Opus 4.8 81.3%
  • PolyMath In use Models solve 9,000 parallel math problems in 18 languages across four difficulty levels, from school math to frontier math. Final answers are checked. Qwen3.7-Max 86.5%
  • USAMO 2026 In use Models write full proofs for the six problems of the 2026 USA Mathematical Olympiad. Judges grade each proof from 0 to 7 against rubrics. GPT-5.5 98.2%