Benchmark Almanac

NewsBench (Forum AI)

GPT-5.6 Terra 88.3% leads since July 2026
Not in model cards

Models answer questions about current events. Judges calibrated against expert ratings score factual accuracy, neutrality, and source quality.

Forum AI publishes scores for eight models on its August election questions. Its factual accuracy score counts answers with no false claims.

Made by
Forum AI
Released
May 2026
Kind
Long-form factuality
Level
Everyday
Scored
Graded by a model
Answers
Open-ended
Measures
Propensity
Risk
Elections
Behavior
Hallucination, Bias
Language
English
In and out
Text → Text
Interaction
Single turn
Run by
A host
Strongest model tested
Claude Opus 5 #11 on the capability index
Last model added
August 2026
Scores refreshed
November 20th, 2026
8
Models scored on its own leaderboard

GPT-5.6 Terra leads with 88.3% among models released by August 2026

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.

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

  1. 1 GPT-5.6 Terra 88.3%
  2. 2 Kimi K3 82.4%
  3. 3 Qwen 3.8 Max 80%
  4. 4 Grok 4.5 79.5%
  5. 5 Gemini 3.6 Flash 76.5%
  6. 6 Claude Opus 5 74.4%
  7. 7 GLM-5.2 74.2%
  8. 8 DeepSeek-V4-Pro 68.2%

Source: Official NewsBench (Forum AI) leaderboard

#ModelScoreSettingDateSource
1 GPT-5.6 Terra 88.3% Jul 2026 Official leaderboard
2 Kimi K3 82.4% Jul 2026 Official leaderboard
3 Qwen 3.8 Max 80% Aug 2026 Official leaderboard
4 Grok 4.5 79.5% Jul 2026 Official leaderboard
5 Gemini 3.6 Flash 76.5% Jul 2026 Official leaderboard
6 Claude Opus 5 74.4% Jul 2026 Official leaderboard
7 GLM-5.2 74.2% Jun 2026 Official leaderboard
8 DeepSeek-V4-Pro 68.2% Apr 2026 Official leaderboard

Rankings by part

We read 3 parts from the benchmark’s own leaderboard: Neutrality, Factuality and Source Quality. Each ranks models on one part of the test. Claude Opus 5 leads 1 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

Neutrality

8 models we track have a score here.

  1. 1 Claude Opus 5 ↑5 98.4%
  2. 2 Kimi K3 96.7%
  3. 3 Qwen 3.8 Max 96.3%
  4. 4 GPT-5.6 Terra ↓3 94.4%
  5. 5 Gemini 3.6 Flash 94.2%
  6. 6 Grok 4.5 ↓2 94.1%
  7. 7 DeepSeek-V4-Pro ↑1 87%
  8. 8 GLM-5.2 ↓1 83.2%

4 models have held number one on the official leaderboard since its release in May 2026

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

DeepSeek Z.ai xAI OpenAI
Own leaderboard Passed 85% in Jul 2026, by GPT-5.6 Terra

Source: Official NewsBench (Forum AI) leaderboard

GPT-5.6 Terra on the official leaderboard passed 85% in July 2026

That was 2 months after its release. By the same age, 21% of the benchmarks from 2026 had passed 85%. All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) GPT-5.6 Terra Grok 4.5 GLM-5.2 DeepSeek-V4-Pro 0% 20% 40% 60% 80% 100% 2026 Near the ceiling (85%) GPT-5.6 Terra Grok 4.5

Source: Official NewsBench (Forum AI) 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 Factuality

All 164 in Factuality
  • SimpleVQA In use Models answer 2,025 short factual questions about images across 9 tasks and 9 topics. An LLM judge grades answers against fixed references. Qwen3.7-Plus 81.7%
  • HallusionBench In use Models answer 1,129 yes or no questions about 346 images, built in pairs to expose language hallucination and visual illusion. Scored by accuracy. Keye-VL-2.0-30B-A3B 73.5%
  • SimpleQA Verified In use 1,000 human-verified, de-duplicated short-answer factual questions measuring parametric knowledge. Gemini 3.1 Pro 77.5%
  • AA-Omniscience v1.1 In use Models answer 3,000 knowledge questions in six domains without tools and may abstain. The index adds correct answers and subtracts wrong ones. Inkling 2 Small 16.1
  • GaRAGe In use Models write long-form RAG answers to 2,366 questions with human-annotated grounding passages. Scoring checks whether answers use the relevant passages. Amazon Nova Pro 60.7%
  • Kimi Hallu Bench In use Models answer hard prompts drawn from practical work tasks. Fact-checking agents score the share of claims that are hallucinated. GPT-6 Astra 4.20%

Data audit

8 of 9 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark

Catalog record 1 warning 1 pass
  • Warning Task access We don’t know whether the tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (8 entries).
  • Pass Models scored 8 models we track.
  • Pass Newest score The newest is from August 2026, for Qwen 3.8 Max.
  • Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is Claude Opus 5 (#11).
  • Note Headroom Saturated. The best is 88.3%, past 85% since July 2026.
Leaderboard import 3 pass
  • Pass Importer We read the board on byforum.com: 8 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.

How we check