Benchmark Almanac

Anthropic political even-handedness eval

Claude Opus 5.5 99.4% leads since September 2026
Grok 4 96% leads since November 2025
Claude Opus 5.5 99.4% leads since September 2026
Only in system cards

Models answer paired prompts that take opposing sides on 150 US political topics. A grader scores even-handedness, refusals and acknowledgment of opposing views.

Made by
Anthropic
Released
November 2025
Kind
Bias, fairness and politics
Level
Everyday
Scored
Graded by a model
Answers
Open-ended
Tasks
All public
Strongest model tested
Claude Fable 5.2 #1 on the capability index
Last in a system card
November 2026
Last model added
November 2026
Scores refreshed
November 12th, 2026
14
Models scored in lab cards
16
System cards report it, from 1 lab

Claude Opus 5.5 leads with 99.4%

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.

Grok 4 leads with 96% across all independent runs

Best score per model across the official leaderboard, Epoch AI’s own runs and any board Epoch AI copied. Each bar and row names its source.

Claude Opus 5.5 leads with 99.4%, claims included

Best score per model from every source, including labs’ own numbers and claims Epoch AI collected from reports and papers. Labs pick their own settings, so a claim can beat an independent run of the same model.

14 models. Scroll sideways for the rest.

  1. 99.4 Claude Opus 5.5
  2. 99.1 Claude Fable 5.2
  3. 98.4 Claude Sonnet 4.6
  4. 98.3 Claude Fable 5.1
  5. 98.2 Claude Opus 4.6
  6. 97.9 Claude Sonnet 5.5
  7. 97.7 Claude Haiku 5.5
  8. 97.6 Claude Fable 5
  9. 96.7 Claude Opus 4.8
  10. 96.4 Claude Sonnet 5
  11. 96.3 Claude Opus 5
  12. 96.0 Claude Opus 4.5
  13. 95.1 Claude Opus 4.7
  14. 94.5 Claude Mythos Preview
  1. 1 Claude Opus 5.5 99.4%
  2. 2 Claude Fable 5.2 99.1%
  3. 3 Claude Sonnet 4.6 98.4%
  4. 4 Claude Fable 5.1 98.3%
  5. 5 Claude Opus 4.6 98.2%
  6. 6 Claude Sonnet 5.5 97.9%
  7. 7 Claude Haiku 5.5 97.7%
  8. 8 Claude Fable 5 97.6%
  9. 9 Claude Opus 4.8 96.7%
  10. 10 Claude Sonnet 5 96.4%
  11. 11 Claude Opus 5 96.3%
  12. 12 Claude Opus 4.5 96%
  13. 13 Claude Opus 4.7 95.1%
  14. 14 Claude Mythos Preview 94.5%

Source: Labs’ model cards

Source: Official Anthropic political even-handedness eval leaderboard

19 models. Scroll sideways for the rest.

  1. 99.4 Claude Opus 5.5
  2. 99.1 Claude Fable 5.2
  3. 98.4 Claude Sonnet 4.6
  4. 98.3 Claude Fable 5.1
  5. 98.2 Claude Opus 4.6
  6. 97.9 Claude Sonnet 5.5
  7. 97.7 Claude Haiku 5.5
  8. 97.6 Claude Fable 5
  9. 96.7 Claude Opus 4.8
  10. 96.4 Claude Sonnet 5
  11. 96.3 Claude Opus 5
  12. 96.0 Grok 4
  13. 96.0 Claude Opus 4.5
  14. 95.1 Claude Opus 4.7
  15. 95.0 Claude Opus 4.1
  16. 94.5 Claude Mythos Preview
  17. 94.0 Claude Sonnet 4.5
  18. 89.0 GPT-5
  19. 66.0 Llama 4 Maverick
  1. 1 Claude Opus 5.5 99.4%
  2. 2 Claude Fable 5.2 99.1%
  3. 3 Claude Sonnet 4.6 98.4%
  4. 4 Claude Fable 5.1 98.3%
  5. 5 Claude Opus 4.6 98.2%
  6. 6 Claude Sonnet 5.5 97.9%
  7. 7 Claude Haiku 5.5 97.7%
  8. 8 Claude Fable 5 97.6%
  9. 9 Claude Opus 4.8 96.7%
  10. 10 Claude Sonnet 5 96.4%
  11. 11 Claude Opus 5 96.3%
  12. 12 Grok 4 thinking; system prompt 96%
  13. 13 Claude Opus 4.5 96%
  14. 14 Claude Opus 4.7 95.1%
  15. 15 Claude Opus 4.1 95%
  16. 16 Claude Mythos Preview 94.5%
  17. 17 Claude Sonnet 4.5 94%
  18. 18 GPT-5 low reasoning; no system prompt 89%
  19. 19 Llama 4 Maverick system prompt 66%

Sources: Labs’ model cards and official Anthropic political even-handedness eval leaderboard

#ModelScoreSettingDateSource
1 Claude Opus 5.5 99.4% Sep 2026 Lab model card
2 Claude Fable 5.2 99.1% Nov 2026 Lab model card
3 Claude Sonnet 4.6 98.4% Feb 2026 Lab model card
4 Claude Fable 5.1 98.3% Sep 2026 Lab model card
5 Claude Opus 4.6 98.2% Feb 2026 Lab model card
6 Claude Sonnet 5.5 97.9% Sep 2026 Lab model card
7 Claude Haiku 5.5 97.7% Oct 2026 Lab model card
8 Claude Fable 5 97.6% Jun 2026 Lab model card
9 Claude Opus 4.8 96.7% May 2026 Lab model card
10 Claude Sonnet 5 96.4% Jun 2026 Lab model card
11 Claude Opus 5 96.3% Jul 2026 Lab model card
12 Claude Opus 4.5 96% Nov 2025 Lab model card
13 Claude Opus 4.7 95.1% Apr 2026 Lab model card
14 Claude Mythos Preview 94.5% Apr 2026 Lab model card
#ModelScoreSettingDateSource
1 Grok 4 96% thinking; system prompt Jul 2025 Official leaderboard
2 Claude Opus 4.1 95% Aug 2025 Official leaderboard
3 Claude Sonnet 4.5 94% Sep 2025 Official leaderboard
4 GPT-5 89% low reasoning; no system prompt Aug 2025 Official leaderboard
5 Llama 4 Maverick 66% system prompt Apr 2025 Official leaderboard
#ModelScoreSettingDateSource
1 Claude Opus 5.5 99.4% Sep 2026 Lab model card
2 Claude Fable 5.2 99.1% Nov 2026 Lab model card
3 Claude Sonnet 4.6 98.4% Feb 2026 Lab model card
4 Claude Fable 5.1 98.3% Sep 2026 Lab model card
5 Claude Opus 4.6 98.2% Feb 2026 Lab model card
6 Claude Sonnet 5.5 97.9% Sep 2026 Lab model card
7 Claude Haiku 5.5 97.7% Oct 2026 Lab model card
8 Claude Fable 5 97.6% Jun 2026 Lab model card
9 Claude Opus 4.8 96.7% May 2026 Lab model card
10 Claude Sonnet 5 96.4% Jun 2026 Lab model card
11 Claude Opus 5 96.3% Jul 2026 Lab model card
12 Grok 4 96% thinking; system prompt Jul 2025 Official leaderboard
13 Claude Opus 4.5 96% Nov 2025 Lab model card
14 Claude Opus 4.7 95.1% Apr 2026 Lab model card
15 Claude Opus 4.1 95% Aug 2025 Official leaderboard
16 Claude Mythos Preview 94.5% Apr 2026 Lab model card
17 Claude Sonnet 4.5 94% Sep 2025 Official leaderboard
18 GPT-5 89% low reasoning; no system prompt Aug 2025 Official leaderboard
19 Llama 4 Maverick 66% system prompt Apr 2025 Official leaderboard

The benchmark's own leaderboard has 6 entries, 5 of them models we track. Switch the scores above to rank them together.

4 models have held number one in labs’ own numbers since its release in November 2025 Number one over time 4 models have held number one with claims included since its release in November 2025

Lab claims count from the day the card came out, independent runs from the model’s release. We draw one row each for the benchmark’s own leaderboard and what labs claim in their cards.

xAI Anthropic
Own leaderboard Passed 85% in Nov 2025, by Grok 4
Grok 4 96%
Lab claims Passed 85% in Nov 2025, by Claude Opus 4.5
Claude Opus 5.5 99.4%

Sources: Official Anthropic political even-handedness eval leaderboard and labs’ model cards

Grok 4 on the official leaderboard passed 85% in July 2025

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

On the benchmark’s own leaderboard Reported by the lab in its model card Best so far
0% 20% 40% 60% 80% 100% 2025 2026 2027 Near the ceiling (85%) Claude Opus 5.5 Claude Sonnet 4.6 Grok 4 Llama 4 Maverick 0% 20% 40% 60% 80% 100% 2025 2026 2027 Near the ceiling (85%) Claude Opus 5.5 Grok 4

Sources: Official Anthropic political even-handedness eval leaderboard and labs’ model cards

Labs report it only in system cards

We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark. Some system cards do, below.

16 system cards report it, from 1 lab

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
Nov 9, 2026 Claude Fable 5.2 system card 99.1 Pairwise political bias, even-handedness, API without a system prompt. Claude.ai 99.7%. Opposing perspectives: API 38.4%, claude.ai 69.3% (Figures 4.4.1.A to 4.4.1.C and Section 4.4.1) Bias
Oct 7, 2026 Claude Haiku 5.5 system card 97.7 Political even-handedness, API without system prompt (claude.ai 99.1). Opposing perspectives 35.9, refusals 3.3 on API (4.4.1) Bias
Sep 28, 2026 Claude Sonnet 5.5 system card 97.9 Political even-handedness, API without system prompt (claude.ai 99.0%), opposing perspectives 41.4% (4.4.1, Figure 4.4.1.A) Bias
Sep 22, 2026 Claude Opus 5.5 system card 99.4 Political even-handedness, 1,350 prompt pairs, API without a system prompt (claude.ai 99.5%), opposing perspectives 26.9% on the API (4.4.1, Figures 4.4.1.A to C) Bias
Sep 1, 2026 Claude Fable 5.1 system card 98.3 Pairwise political bias, even-handedness, API without a system prompt (claude.ai 98.8%); opposing perspectives 25.9% (claude.ai 80.5%), refusals 2.1% (claude.ai 5.0%) (Figures 4.4.1.A to 4.4.1.C) Bias
Jul 24, 2026 Claude Opus 5 system card 96.3 Political even-handedness, 1,350 prompt pairs, API without a system prompt (claude.ai 98.9%). Opposing perspectives 46.9% and refusals 3.0% on the API (75.8% and 4.2% on claude.ai), printed on charts (4.4.1, Figures 4.4.1.A and B) Bias
Jun 30, 2026 Claude Sonnet 5 system card 96.4 Political even-handedness, 1,350 prompt pairs, public system prompt applied, opposing perspectives 54.6%, refusals 4.7% (4.4.1, Figure 4.4.1.A) Bias
Jun 9, 2026 Claude Fable 5 system card 97.6 Pairwise political bias, even-handedness, public system prompt applied; opposing perspectives 70.0%, refusals 13.3%, printed on chart (Figure 4.4.1.A) Bias
May 28, 2026 Claude Opus 4.8 system card 96.7 Political even-handedness, 1,350 prompt pairs, public system prompt applied, thinking on and off pooled. Opposing perspectives 66.4%, refusals 7.2%, printed on chart (4.4.1, Figure 4.4.1.A) Bias
Apr 16, 2026 Claude Opus 4.7 system card 95.1 Pairwise political bias, even-handedness with the public system prompt, no thinking, printed on chart. Opposing perspectives 40.1, refusals 6.7 (4.5.1, Figure 4.5.1.A) Bias
Apr 7, 2026 Claude Mythos Preview system card 94.5 Political even-handedness with public system prompt, no thinking; opposing perspectives 47.0, refusals 13.5 (Table 8.2.1.A) Bias
Feb 17, 2026 Claude Sonnet 4.6 system card 98.4 Political even-handedness with system prompt, no thinking; opposing perspectives 32.1, refusals 4.5 (Table 3.5.1.A) Bias
Feb 5, 2026 Claude Opus 4.6 system card 98.2 Political even-handedness, 1,350 prompt pairs, public system prompt, no thinking; opposing perspectives 44.6, refusals 4.5 (Table 3.5.1.A) Bias
Nov 24, 2025 Claude Opus 4.5 system card 96 Political even-handedness, 1,350 prompt pairs, public system prompt, no extended thinking (Figure 3.5.1.A 0.96; opposing perspectives 0.40, refusals 0.04) Bias
Oct 15, 2025 Claude Haiku 4.5 system card Political bias, paired prompts, substantial asymmetry rate 5.3% in standard thinking and 10% across standard and extended thinking, lower is better, no even-handedness score (2.5.1) Bias
Sep 29, 2025 Claude Sonnet 4.5 system card Political bias, paired prompts, substantial asymmetry rate 3.3% averaged over thinking on and off (1.3% with extended thinking, 5.3% without), lower is better, no even-handedness score (2.5.1) Bias

More in Safety and alignment

All 465 in Safety and alignment
  • FORTRESS In use Paired adversarial and benign national-security misuse prompts. Rubric-graded risk score on adversarial and over-refusal score on benign prompts. Claude Opus 5.5 5.78%
  • StrongREJECT In use Forbidden-prompt jailbreak benchmark with a rubric grader that scores how useful a non-refusal actually is. Inkling 98.6%
  • Gray Swan IPI Arena benchmark In use Indirect prompt-injection attacks from public red-teaming competitions replayed on tool, coding and browser agents. Attack success rate at k attempts. Gemini 4 Carbon 0%
  • DistressBench In use Models reply as a chatbot to 718 simulated users in psychological crisis, in single-turn and multi-turn chats. Three judge models score replies against clinician-written rubrics. Muse Spark 1.2 88.4%
  • Lakera B3 (Backbone Breaker Benchmark) In use Crowdsourced prompt-injection attacks hit backbone LLMs inside agent threat snapshots at three defense levels. The score is attack resistance, 100 minus the board's vulnerability percentage. Claude Opus 4.5 89%
  • IHEval In use Models face conflicts between system, user and tool instructions. Reports a composite score for following the higher-priority instruction. GPT-4o 70%