pith. sign in
Pith Number

pith:KUFHIHH4

pith:2026:KUFHIHH4IF4BZMYVMXRN37C5JO
not attested not anchored not stored refs resolved

Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs

Chenhao Sun, Ivo Petrov, Jasper Dekoninck, K\'ari R\"ognvaldsson, Martin Vechev, Nikola Jovanovi\'c, Tim Gehrunger

Expanding MathArena to proofs and research questions shows frontier LLMs solve 98% of 2026 USAMO problems.

arxiv:2605.00674 v2 · 2026-05-01 · cs.CL

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{KUFHIHH4IF4BZMYVMXRN37C5JO}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp
2 Internet Archive
3 Author claim open · sign in to claim
4 Citations open
5 Replications open
Portable graph bundle live · download bundle · merged state
The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

Notably, the strongest model, GPT-5.5, now reaches 98% on the 2026 USA Math Olympiad and 74% on research-level questions, showing that frontier models can now comfortably solve extremely challenging mathematical problems.

C2weakest assumption

The new benchmarks and evaluation protocol remain free of training-data contamination and fairly measure genuine reasoning rather than memorization or benchmark-specific shortcuts.

C3one line summary

MathArena is broadened into a maintained platform with new benchmarks for proofs, research questions, and formal verification, where GPT-5.5 scores 98% on 2026 USAMO and 74% on research-level tasks.

References

110 extracted · 110 resolved · 5 Pith anchors

[6] Wei-Lin Chiang, Lianmin Zheng, Ying Sheng, Anastasios Nikolas Angelopoulos, Tianle Li, Dacheng Li, Banghua Zhu, Hao Zhang, Michael I. Jordan, Joseph E. Gonzalez, and Ion Stoica. Chatbot arena: An open 2024
[7] Ai model & api providers analysis
[8] Accessed: 2026-04-13 2026
[9] Vals AI. Benchmarks.https://www.vals.ai/benchmarks, 2026. Accessed: 2026-04-13 2026
[10] MathArena: Evaluating LLMs on Uncontaminated Math Competitions · arXiv:2505.23281

Formal links

2 machine-checked theorem links

Cited by

9 papers in Pith

Receipt and verification
First computed 2026-05-20T00:01:42.392550Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

550a741cfc41781cb31565e2ddfc5d4bb3fc1167ab9b3ddcfc8ea92ff58eaf57

Aliases

arxiv: 2605.00674 · arxiv_version: 2605.00674v2 · doi: 10.48550/arxiv.2605.00674 · pith_short_12: KUFHIHH4IF4B · pith_short_16: KUFHIHH4IF4BZMYV · pith_short_8: KUFHIHH4
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/KUFHIHH4IF4BZMYVMXRN37C5JO \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 550a741cfc41781cb31565e2ddfc5d4bb3fc1167ab9b3ddcfc8ea92ff58eaf57
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "f2de4624f6470c58c9995a5f89759c13962d99f1460444f83ddc681705973ef1",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2026-05-01T13:56:34Z",
    "title_canon_sha256": "81650e89f738211c5de46e0d9f3372b37e7c2953c81b63a0d9e9f19156d4c92d"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.00674",
    "kind": "arxiv",
    "version": 2
  }
}